[{"_1":2,"_1365":-5,"_1366":-5},"loaderData",{"_3":4,"_9":10,"_32":33,"_1363":-5,"_1364":-5},"routes/layout",{"_5":6},"envVars",{"_7":8},"ANALYTICS","https://d1ibcrisv2qlq9.cloudfront.net/event","mlg",{"_11":9,"_12":13},"podcastKey","show",{"_14":15,"_16":17,"_18":19,"_20":21,"_22":23,"_24":25,"_26":27,"_28":29,"_30":31},"title","Machine Learning Guide","link","https://ocdevel.com/mlg","feed","http://ocdevel.com/files/podcasts/machine-learning/feed.xml","keywords","machine,learning,ml,introduction,artificial,intelligence,ai","image","http://ocdevel.com/files/podcasts/machine-learning/art.jpg","date",["D",1485932400000],"teaser","Machine learning audio course. Teaches ML fundamentals, models (shallow and deep), math, and more.","body","MLG is a machine learning podcast teaching the fundamentals of machine learning and artificial intelligence. It covers intuition, models, neural networks, math, languages, frameworks, and more. Podcasts are a great supplement during exercise, commute, chores, etc. The resources section provides a syllabus for machine learning videos, courses, books, and audio.","useLibsynPlayer",true,"mlg._podcast.$id",{"_34":35,"_11":9,"_12":1339,"_1341":1342,"_1361":-5,"_1362":-7},"resources",{"_36":37,"_1335":1336,"_1337":1338},"flat",{"_38":39,"_68":69,"_80":81,"_86":87,"_92":93,"_120":121,"_138":139,"_157":158,"_202":203,"_216":217,"_228":229,"_237":238,"_247":248,"_257":258,"_268":269,"_280":281,"_297":298,"_309":310,"_329":330,"_342":343,"_352":353,"_362":363,"_371":372,"_381":382,"_391":392,"_401":402,"_413":414,"_421":422,"_433":434,"_445":446,"_455":456,"_463":464,"_472":473,"_481":482,"_489":490,"_498":499,"_510":511,"_523":524,"_535":536,"_545":546,"_554":555,"_568":569,"_583":584,"_592":593,"_601":602,"_609":610,"_620":621,"_628":629,"_638":639,"_653":654,"_665":666,"_673":674,"_681":682,"_693":694,"_701":702,"_709":710,"_726":727,"_736":737,"_745":746,"_756":757,"_766":767,"_775":776,"_783":784,"_797":798,"_807":808,"_817":818,"_825":826,"_834":835,"_843":844,"_852":853,"_859":860,"_867":868,"_877":878,"_886":887,"_896":897,"_906":907,"_916":917,"_924":925,"_940":941,"_950":951,"_959":960,"_969":970,"_977":978,"_985":986,"_993":994,"_1001":1002,"_1009":1010,"_1017":1018,"_1025":1026,"_1033":1034,"_1043":1044,"_1048":1049,"_1055":1056,"_1060":1061,"_1065":1066,"_1073":1074,"_1082":1083,"_1090":1091,"_1098":1099,"_1105":1106,"_1113":1114,"_1119":1120,"_1126":1127,"_1133":1134,"_1140":1141,"_1149":1150,"_1158":1159,"_1165":1166,"_1175":1176,"_1185":1186,"_1194":1195,"_1202":1203,"_1210":1211,"_1217":1218,"_1225":1226,"_1238":1239,"_1246":1247,"_1256":1257,"_1268":1269,"_1279":1280,"_1288":1289,"_1297":1298,"_1306":1307,"_1313":1314,"_1321":1322,"_1328":1329},"676811f178ca2bc4cede36d2b9c35596",{"_40":41,"_42":43,"_44":45,"_46":47,"_48":49,"_50":51,"_52":38,"_53":54,"_55":56,"_57":31,"_58":31,"_59":45,"_9":60,"_63":31,"_64":65,"_66":67},"importance","valuable","format","video","difficulty","medium","engagement","passive","topic","cv","relevance","fresh","id","t","(TODO) Relevant Lectures from CS231n / Advanced ML Courses","d","

Dedicated, comprehensive courses on just generative models are still solidifying. Look for lectures on Generative Models, GANs, VAEs, and Diffusion within the latest iterations of advanced courses like Stanford's CS231n (CV) or similar university offerings for structured video content. Search syllabi/lecture lists of recent top ML/CV courses.

\n","itunesu","audioOption","video2audio",[61,62],"9","25","hide","key","mlg_todorelevantlectures","links",[],"5abbd0e9981f192c20ddea37b003af23",{"_40":70,"_42":71,"_44":72,"_46":47,"_48":73,"_50":51,"_52":68,"_53":74,"_55":75,"_76":31,"_77":31,"_64":78,"_66":79},"supplementary","other","easy","basics","TODO: Organize","

I'm still wrestling with the resources for the DL sub-fields. So much has changed, and there's been an explosion of resources. I'm going to dump my notes here in case it's valuable; and I'll incorporate them as gold-standard picks above over time.

Stanford Courses

https://www.youtube.com/@stanfordonline/playlists. I'm still trying to figure out their system. Stanford had the best YouTube lecture recordings for a while, but they started pulling some resources due to legal battles. And they started becoming disorganized. They have dedicated YouTube channels for Stanford, Stanford Online, and Stanford Engineering. If you figure out their system, please let me know.

MIT Courses

Similar to Stanford, I'm having trouble groking their organization. Here's one playlist as a starting point https://www.youtube.com/watch?v=alfdI7S6wCY&list=PLtBw6njQRU-rwp5__7C0oIVt26ZgjG9NI. And again, if you figure out their organization strategy, please let me know.

Deep Learning for Computer Vision - Michigan Online

https://www.youtube.com/playlist?list=PL5-TkQAfAZFbzxjBHtzdVCWE0Zbhomg7r. This covers a lot of DL territory, with special focus on Generative models in images & video. I'm going to explore this more to determine if it makes the cut above.

3Blue1Brown

https://www.3blue1brown.com/topics/neural-networks I need to start sprinkling this series throughout my whole resources tree. The best animated learning series I've ever seen; and covers a lot of topics in ML / DL / math, etc. Description:

Unmatched for visually explaining the core mathematical concepts behind calculus, linear algebra, and neural networks (including backpropagation). While not a full DL course, the \"Neural Networks\" series is essential viewing for understanding how they work, complementing more implementation-focused resources. It provides the

#topic:dl:basics #format:video #price:free

Jay Alammar

https://jalammar.github.io/illustrated-transformer/. Visual Explanations (Especially Transformers/NLP) / Articles/Blog Posts. Description:

Jay Alammar's blog posts, particularly \"The Illustrated Transformer\" and \"Illustrated Word2vec\", are considered the go-to visual explanations for these fundamental NLP/LLM concepts. They break down complex architectures into understandable components with clear diagrams. Essential reading before or alongside technical papers/courses.

#topic:nlp #price:free #format:other

Andrej Karpathy

https://karpathy.github.io/, https://www.youtube.com/@AndrejKarpathy Articles/Blog Posts, Videos (Talks/Coding Sessions). Description:

Beyond the specific \"Let's Build GPT\" video already mentioned, Karpathy's blog posts (like \"The Unreasonable Effectiveness of Recurrent Neural Networks\") and various conference talks provide deep insights into how models work, training dynamics, and practical considerations. Less structured than a course, but high value.

#topic:cv:nlp:dl #price:free #format:other:video

\n","info","lefthere","mlg_todoorganize",[],"82de9e4b261c78ebd70606ec74edadb5",{"_40":70,"_42":71,"_44":72,"_46":47,"_48":73,"_50":51,"_52":80,"_53":82,"_55":83,"_76":31,"_64":84,"_66":85},"Why Computer Science?","

General Computer Science Master's degrees is recommended, even for students primarily interested in ML / AI / DS.

Foundational Strength & Future-Proofing: This is a major factor. Core CS principles (algorithms, data structures, systems, theory) are the bedrock upon which ML/AI is built. Understanding these deeply allows for better comprehension of why ML algorithms work, how to optimize them, how to integrate them into larger systems, and critically, how to adapt when the AI landscape inevitably shifts. A strong CS foundation makes you a more versatile and resilient engineer/scientist.
Industry Perception: Many top tech companies and research labs still hold a traditional, rigorous CS education in very high regard, even for specialized roles. They often prefer candidates with strong fundamental CS skills, knowing they can train them on specific ML libraries or techniques. A degree from a top-ranked CS department like Georgia Tech or UT Austin carries significant weight. While specialized degrees are gaining acceptance, the prestige and recognition of a core CS degree from these institutions are arguably still more universally acknowledged, especially outside niche AI startups.
Specialization Within the Degree: Crucially, these are not just generic CS degrees. Both OMSCS and MSCSO offer specific specializations or sufficient elective flexibility to create a deep focus in Machine Learning, AI, Robotics, Data Science, etc. Students can tailor their coursework heavily towards their interests while still benefiting from the broader CS context and degree title. For example, the OMSCS ML specialization is very comprehensive.
\"De-Facto\" Status & Value Proposition: OMSCS and MSCSO have established themselves as the benchmarks for affordable, high-quality, online graduate CS education from top-tier universities. While reputable online Master's programs specifically titled \"Data Science\" or \"Artificial Intelligence\" do exist now (e.g., programs from UIUC, Stanford, Berkeley often have online components or related degrees, though often much pricier or with different structures), none have quite achieved the unique combination of low cost, widespread recognition, and established track record that OMSCS and MSCSO possess in the online space. They remain the clearest \"de-facto\" choices when balancing quality, cost, and reputation for an online Master's relevant to ML/AI.
Avoiding Over-Specialization Risk: Sometimes, hyper-specialized degrees can be perceived as narrower or potentially fad-driven (though ML/AI is hardly a fad, the specific focus of a degree might age). A CS degree signals broader capability.

While good specialized online ML/AI/DS Master's programs are emerging, the general CS Master's from top-tier, affordable online programs like OMSCS and MSCSO currently represents the most robust, widely respected, future-proof, and high-value \"de-facto\" recommendation for someone seeking a formal online graduate credential to enter or advance in the field. They provide the essential foundations and the opportunity to specialize deeply.

\n","mlg_whycomputerscience",[],"94b21c914a2dda6c796dbb64d64cf618",{"_40":70,"_42":71,"_44":72,"_46":47,"_48":73,"_50":51,"_52":86,"_53":88,"_55":89,"_64":90,"_66":91},"Two Minute Papers","

Excels at creating short (often slightly longer than two minutes, despite the name!), digestible video summaries of cutting-edge scientific research papers, with a strong focus on AI, machine learning, computer graphics, and robotics. Its major strength and defining characteristic are the visuals. Dr. Zsolnai-Fehér uses clips, diagrams, and results from the papers he discusses to make complex concepts much more understandable. The visual component is integral to the experience. While you can listen to YouTube videos as audio-only, Two Minute Papers doesn't have a dedicated, official audio podcast feed. Furthermore, listening without the visuals would mean missing a significant part of the explanation and context, especially for papers dealing with visual results (like image generation, simulation, or robotics). Some sources specifically state it's not a podcast but include it in lists due to its value for staying updated efficiently.

\n","mlg_twominutepapers",[],"5a5bfa29d15b2102afdd046ae427d8ab",{"_40":94,"_42":95,"_44":96,"_46":97,"_48":73,"_50":51,"_52":92,"_53":98,"_55":99,"_100":101,"_9":102,"_111":112,"_64":113,"_66":114},"essential","course","hard","active","Andrew Ng - Machine Learning Specialization","

This collaboration of Coursera, DeepLearning.AI, and Stanford is the modern, Python-based successor to Andrew Ng's original, highly influential Coursera course. Taught by Andrew Ng, it covers fundamental supervised and unsupervised machine learning concepts, practical advice, and implementation in Python. It's widely considered the starting point for many self-learners getting into ML fundamentals. Completing the specialization provides a certificate demonstrating foundational knowledge from a leading expert.

\n","price","free",[103,104,105,106,107,108,109,110],"1","2","4","5","7","12","13","14","mla",[103],"mlg_andrewngmachinelearn",[115],{"_53":116,"_117":118,"_119":101},"Coursera","l","http://imp.i384100.net/kOJJrL","p","16db5e8c4de7aff9ad378f265e8669a9",{"_40":94,"_42":122,"_44":45,"_46":47,"_48":123,"_50":51,"_52":120,"_53":125,"_55":126,"_9":127,"_111":131,"_64":132,"_66":133},"book",[124,73],"tech","Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow (3rd Edition)","

This book by Aurélien Géron is widely considered the golden standard practical companion for learning ML. The 3rd edition (late 2022) is crucial as it updates the second half to use Keras 3, which can run on TensorFlow, PyTorch, or JAX backends, mitigating concerns about being locked into TensorFlow. The first half provides an excellent practical tour of fundamental ML concepts using Scikit-Learn, complementing Ng's course perfectly. It teaches how to build, train, and evaluate models using industry-standard tools. Essential for bridging theory and practice.

Note: PyTorch has gained significant popularity, especially in the research community, due to its Pythonic feel and dynamic computation graphs. But HOML remains a the top pick here for the following reasons.

Foundational ML (Part 1): Scikit-Learn is King: The first ~10 chapters of HOML, which cover the core \"Basics\" of machine learning (linear/logistic regression, SVMs, trees, ensembles, dimensionality reduction, clustering), primarily use Scikit-Learn. Scikit-Learn is the industry standard library for these algorithms and is completely framework-agnostic. Whether you use TensorFlow or PyTorch for deep learning later, you will use Scikit-Learn for these foundational tasks. This crucial part of the book is unaffected by the TensorFlow/PyTorch debate.
Deep Learning (Part 2): Keras 3 is Multi-Backend: This is the key change in the 3rd edition. The second half of the book, which introduces neural networks and deep learning, uses Keras 3.
- Keras 3 is Framework-Agnostic: Unlike earlier versions that were tightly integrated with TensorFlow, Keras 3 is designed to run on multiple backends, including TensorFlow, PyTorch, and JAX.
- You Choose the Backend: You can configure Keras 3 to use PyTorch as its backend. While the book's code examples might originate from a TensorFlow context (since Keras was historically TF-based), the Keras API itself is consistent. Learning Keras 3 allows you to leverage its user-friendly API while having the option to run it on a PyTorch backend.
- Benefits: This means the deep learning concepts and Keras API skills you learn are transferable. You are not locked into TensorFlow. You can write Keras code and execute it using PyTorch.
\n

\n",[61,128,108,109,129,130],"10","24","29",[104,106,107,110],"mlg_handsonmachinelearni",[134],{"_53":135,"_117":136,"_119":137},"Amazon","https://amzn.to/4cwF2m6","$","7e48ef2c3483b0a203c4dc2417a95129",{"_40":94,"_42":140,"_44":96,"_46":97,"_48":141,"_50":51,"_52":138,"_53":142,"_55":143,"_100":101,"_9":144,"_64":146,"_66":147},[122,95],"math","An Introduction to Statistical Learning (ISLR) (2nd Edition)","

While Ng provides intuition and HOML provides practice, ISLR offers the most accessible yet rigorous theoretical grounding in fundamental ML concepts from a statistical perspective. It's considered a more approachable version of the classic \"Elements of Statistical Learning\" (ESL). The 2nd edition includes updated topics and labs available in both R and Python. Understanding the 'why' behind the algorithms is crucial, and ISLR is arguably the best resource for this at the foundational level without being overly mathematical like ESL or PRML. Often used as a university textbook. The authors also provide video lectures.

\n",[104,105,106,107,145,108,109],"8","mlg_anintroductiontostat",[148,151,154],{"_53":149,"_117":150,"_119":101},"PDF","https://www.google.com/url?sa=E&q=https%3A%2F%2Fwww.statlearning.com%2F",{"_53":152,"_117":153,"_119":101},"Python Labs","https://www.google.com/url?sa=E&q=https%3A%2F%2Fgithub.com%2Fintro-stat-learning%2FISLP_labs",{"_53":155,"_117":156,"_119":101},"Videos / Courses","https://www.statlearning.com/online-courses","beac7ca16c9db38b4c8b5a7166ce54e6",{"_40":41,"_42":43,"_44":45,"_46":47,"_48":73,"_50":51,"_52":157,"_53":159,"_55":160,"_58":31,"_59":161,"_9":162,"_111":163,"_64":164,"_66":165},"StatQuest - Machine Learning","

While not a primary structured learning path, StatQuest is the gold standard for intuitive video explanations of specific ML algorithms and statistical concepts. When you hit a wall understanding concepts like PCA, Gradient Boost, Logistic Regression, etc., from Ng's course or ISLR, StatQuest videos provide incredibly clear, visual, and memorable breakdowns. Use this as an essential supplement to clarify concepts as needed. Its popularity and clarity make it a must-have tool in the learning arsenal. There are multiple playlists for various topics, so I'll break out a few in their relevant locations in the resources subtrees.

\n","good",[105,106,107,145,61,108,109,110,62,130],[145],"mlg_statquestmachinelear",[166,169,172,175,178,181,184,187,190,193,196,199],{"_53":167,"_117":168,"_119":101},"YouTube - All Playlists","https://www.youtube.com/c/joshstarmer/playlists",{"_53":170,"_117":171,"_119":101},"Machine Learning","https://www.youtube.com/playlist?list=PLblh5JKOoLUICTaGLRoHQDuF_7q2GfuJF",{"_53":173,"_117":174,"_119":101},"XGBoost","https://www.youtube.com/playlist?list=PLblh5JKOoLULU0irPgs1SnKO6wqVjKUsQ",{"_53":176,"_117":177,"_119":101},"Data","https://www.youtube.com/playlist?list=PLblh5JKOoLUJUNlfvCNhJMNjNNpt5ljcR",{"_53":179,"_117":180,"_119":101},"Neural Networks","https://www.youtube.com/playlist?list=PLblh5JKOoLUIxGDQs4LFFD--41Vzf-ME1",{"_53":182,"_117":183,"_119":101},"SVMs","https://www.youtube.com/playlist?list=PLblh5JKOoLUL3IJ4-yor0HzkqDQ3JmJkc",{"_53":185,"_117":186,"_119":101},"Gradient Boost","https://www.youtube.com/playlist?list=PLblh5JKOoLUJjeXUvUE0maghNuY2_5fY6",{"_53":188,"_117":189,"_119":101},"CART","https://www.youtube.com/playlist?list=PLblh5JKOoLUKAtDViTvRGFpphEc24M-QH",{"_53":191,"_117":192,"_119":101},"Random Forests","https://www.youtube.com/playlist?list=PLblh5JKOoLUIE96dI3U7oxHaCAbZgfhHk",{"_53":194,"_117":195,"_119":101},"Logistic Regression","https://www.youtube.com/playlist?list=PLblh5JKOoLUKxzEP5HA2d-Li7IJkHfXSe",{"_53":197,"_117":198,"_119":101},"Linear Models","https://www.youtube.com/playlist?list=PLblh5JKOoLUIzaEkCLIUxQFjPIlapw8nU",{"_53":200,"_117":201,"_119":101},"Sequencing","https://www.youtube.com/playlist?list=PLblh5JKOoLUJo2Q6xK4tZElbIvAACEykp","43da81389ab31a22fb93897f1ecd5ee9",{"_40":41,"_42":43,"_44":96,"_46":47,"_48":73,"_50":51,"_52":202,"_53":204,"_55":205,"_206":31,"_59":161,"_58":31,"_9":207,"_63":31,"_64":210,"_66":211},"TGC Machine Learning","

Video overview of ML basics, highly amenable to audio-only listening. It's rapid-pace, covering a lot of ground in relatively little time. I recommend this as an early resource, since it will give you an overview of everything. It covers newer material like GANs and RL; and material not often covered in ML-basics resources like, like Bayesian methods.

\n","tgc",[103,104,208,105,106,107,61,108,109,110,209,62,130],"3","16","mlg_tgcmachinelearning",[212],{"_53":213,"_117":214,"_119":215},"TGC","https://thegreatcourses.7eer.net/c/358692/167386/2997?prodsku=9070&u=https%3A%2F%2Fwww.thegreatcourses.com%2Fcourses%2Fintroduction-to-machine-learning&intsrc=PUI1_1204","$$","4142206d6a4b8cb182acc6d8e953c327",{"_40":41,"_42":122,"_44":96,"_46":47,"_48":73,"_50":51,"_52":216,"_53":218,"_55":219,"_9":220,"_63":31,"_64":221,"_66":222},"The Hundred-Page Machine Learning Book","",[103,104,105,106,107,145,61,108,109,110,130],"mlg_thehundredpagemachin",[223,226],{"_53":224,"_117":225,"_119":137},"Website","http://themlbook.com/",{"_53":135,"_117":227,"_119":137},"https://amzn.to/42rseKJ","b40b8e1946d6d201e0fc8e790aae2ee8",{"_40":41,"_42":122,"_44":96,"_46":47,"_48":230,"_50":51,"_52":228,"_53":231,"_55":219,"_9":232,"_63":31,"_64":233,"_66":234},[73,141],"Elements of Statistical Learning",[104,105,106,107,145,108,109,110,130],"mlg_elementsofstatistica",[235],{"_53":135,"_117":236,"_119":137},"https://amzn.to/44wISd5","c3f0c61a5ac864a153b362b948bf626b",{"_40":41,"_42":122,"_44":96,"_46":47,"_48":73,"_50":51,"_52":237,"_53":239,"_55":219,"_9":240,"_63":31,"_64":241,"_66":242},"Pattern Recognition and Machine Learning",[104,105,106,107,145,61,108,109,110,62,130],"mlg_patternrecognitionan",[243,245],{"_53":149,"_117":244,"_119":101},"http://users.isr.ist.utl.pt/~wurmd/Livros/school/Bishop%20-%20Pattern%20Recognition%20And%20Machine%20Learning%20-%20Springer%20%202006.pdf",{"_53":135,"_117":246,"_119":137},"https://amzn.to/3EpBUfk","d93996a22cfead01b72434887de3d908",{"_40":41,"_42":43,"_44":45,"_46":47,"_48":73,"_50":51,"_52":247,"_53":249,"_55":250,"_59":161,"_58":31,"_9":251,"_63":31,"_64":252,"_66":253},"Introduction to Machine Learning for Coders","

Video series part of Fast.ai. You'll use these videos if you're taking the Fast.ai courses, or you can just download the playlist as supplementary audio material

\n",[105,106,107,61,128,108,109,110,129],"mlg_introductiontomachin",[254],{"_53":255,"_117":256,"_119":101},"YouTube","https://www.youtube.com/playlist?list=PLfYUBJiXbdtSyktd8A_x0JNd6lxDcZE96","193fdf4cb17a7fc4ee49e3fe45d2a903",{"_40":94,"_42":95,"_44":96,"_46":97,"_48":73,"_50":259,"_52":257,"_53":260,"_55":261,"_262":31,"_9":263,"_63":31,"_64":264,"_66":265},"dated","Andrew Ng Coursera Course","

[Update 2025-04-15] This has been replaced by the Machine Learning Specialization series (still by Ng on Coursera). I obviously harped very hard on this course through my podcast, so you'll need to find the right weeks that go along with the topics I discussed.

\n","archived",[103,104,105,106,107,108,109,110],"mlg_andrewngcourseracour",[266],{"_53":116,"_117":267,"_119":101},"http://imp.i384100.net/xLzzYk","c377f7bf439e7bfeea9236030cf868d6",{"_40":94,"_42":95,"_44":96,"_46":97,"_48":270,"_50":51,"_52":268,"_53":271,"_55":272,"_100":101,"_9":273,"_111":275,"_64":276,"_66":277},"dl","Andrew Ng - Deep Learning Specialization","

A collaboration of Coursera and DeepLearning.AI, and Andrew Ng, this specialization is the standard follow-up for those wanting to dive into deep learning. It builds strong foundations in neural networks, CNNs, RNNs, optimization, and best practices. Ideal if you want a deep grasp of the mathematical and conceptual underpinnings before diving deep into code. Uses TensorFlow/Keras. Still a highly respected path taken by many professionals.

\n",[274,61,62],"6",[103],"mlg_andrewngdeeplearning",[278],{"_53":116,"_117":279,"_119":101},"http://imp.i384100.net/qzOOYn","2c11546bf6233f6bfd940a2588893073",{"_40":94,"_42":95,"_44":45,"_46":97,"_48":282,"_50":51,"_52":280,"_53":283,"_55":284,"_9":285,"_111":286,"_64":287,"_66":288},[270,124],"Fast.ai Practical Deep Learning for Coders","

The premier, structured course for a practice-first understanding of deep learning. Focuses on getting learners to build and train state-of-the-art models quickly using PyTorch and the fastai library. Teaches concepts through practical application (\"top-down\" approach). Ideal if you learn best by doing and want to achieve results rapidly. Regularly updated. Note: Always refer to course.fast.ai for the latest playlist link

\n",[61,128,129,62],[107],"mlg_fastaipracticaldeepl",[289,291,294],{"_53":224,"_117":290,"_119":101},"http://course.fast.ai/",{"_53":292,"_117":293,"_119":137},"Book","https://amzn.to/4jzIPkW",{"_53":295,"_117":296,"_119":101},"YouTube (2020)","https://www.youtube.com/playlist?list=PLfYUBJiXbdtRL3FMB3GoWHRI8ieU6FhfM","56bf4e1875cd549fb8088914e7379781",{"_40":94,"_42":122,"_44":96,"_46":47,"_48":270,"_50":51,"_52":297,"_53":299,"_55":300,"_9":301,"_64":302,"_66":303},"Deep Learning Book by Goodfellow, Bengio, Courville","

The definitive, comprehensive theoretical reference for deep learning. Covers the mathematical and conceptual foundations in unparalleled depth. While challenging, it's the go-to resource for a deep understanding and serves as an essential companion throughout your learning.

\n",[61,62],"mlg_deeplearningbookbygo",[304,306],{"_53":135,"_117":305,"_119":137},"https://amzn.to/3YuoTrx",{"_53":307,"_117":308,"_119":101},"HTML","http://www.deeplearningbook.org","2c13310cc8ef4293eadd8b40f4439569",{"_40":41,"_42":43,"_44":45,"_46":47,"_48":311,"_50":51,"_52":309,"_53":312,"_55":313,"_57":31,"_58":31,"_59":45,"_9":314,"_64":321,"_66":322},"nlp","Stanford CS224N: NLP with Deep Learning","

Still considered the premier academic course covering foundational and modern NLP techniques, heavily focusing on deep learning approaches. Updated relatively frequently. Combines strong theoretical grounding with practical insights.

\n",[61,315,316,317,318,319,320],"18","19","20","22","23","33","mlg_stanfordcsnnlpwithde",[323,326],{"_53":324,"_117":325,"_119":101},"Website (for latest version)","http://web.stanford.edu/class/cs224n/",{"_53":327,"_117":328,"_119":101},"YouTube (Winter 2023)","https://www.youtube.com/playlist?list=PLoROMvodv4rMFqRtEuo6SGjY4XbRIVRd4","f2bb1bbaeccb8aaf8cabdb3c48766fb7",{"_40":41,"_42":122,"_44":96,"_46":47,"_48":311,"_50":51,"_52":329,"_53":331,"_55":332,"_9":333,"_64":334,"_66":335},"Speech and Language Processing (3rd Ed. Draft) by Jurafsky & Martin","

The definitive, comprehensive reference textbook covering the breadth of NLP theory and methods, from classical to modern deep learning. Less of a tutorial, more of an essential encyclopedia for deep understanding and reference. The online draft is frequently updated.

\n",[61,315,316,317,318,319,320],"mlg_speechandlanguagepro",[336,339],{"_53":337,"_117":338,"_119":101},"PDF (3rd Ed Draft)","https://web.stanford.edu/~jurafsky/slp3/",{"_53":340,"_117":341,"_119":137},"Amazon (2nd Ed Complete)","https://amzn.to/4j7QTJW","41b160de5db2ea290e8f9b282d8ed69c",{"_40":41,"_42":71,"_44":45,"_46":47,"_48":311,"_50":51,"_52":342,"_53":344,"_55":345,"_9":346,"_64":347,"_66":348},"Jay Alammar: \"The Illustrated Transformer\"","

Widely considered the single best conceptual introduction to the Transformer architecture. Breaks down self-attention and the model structure with clear visualizations. Essential reading before diving into code or denser papers.

\n",[61,318,319,320],"mlg_jayalammartheillustr",[349],{"_53":350,"_117":351,"_119":101},"Article","https://jalammar.github.io/illustrated-transformer/","a6202ce552a8c960e347f449033b1a80",{"_40":94,"_42":95,"_44":45,"_46":97,"_48":311,"_50":51,"_52":352,"_53":354,"_55":355,"_9":356,"_111":357,"_64":358,"_66":359},"Hugging Face NLP Course","

The dominant practical resource for learning modern NLP using the Hugging Face ecosystem (Transformers, Datasets, Tokenizers). Hands-on and library-focused, it's essential for applying NLP today. Constantly updated.

\n",[61,128,315,316,317,318,319,320],[128],"mlg_huggingfacenlpcourse",[360],{"_53":224,"_117":361,"_119":101},"https://huggingface.co/learn/nlp-course","949a215c7cd5acd00400da4ea70cdd4b",{"_40":41,"_42":43,"_44":45,"_46":47,"_48":311,"_50":51,"_52":362,"_53":364,"_55":365,"_9":366,"_64":367,"_66":368},"Andrej Karpathy: \"Let's build GPT\"","

An incredibly insightful hands-on coding session building a GPT model from scratch in PyTorch. Demystifies the implementation details and provides intuition unmatched by reading alone. Essential for understanding the mechanics. I highly recommend exploring his channel. Karpathy is a legend in AI, and like Alammar and 3Blue1Brown, has a treasure-trove of playlists and videos.

\n",[61,128,318,319,320],"mlg_andrejkarpathyletsbu",[369],{"_53":255,"_117":370,"_119":101},"https://www.youtube.com/watch?v=kCc8FmEb1nY","3bd1009f7f870a45958e42df5337a697",{"_40":41,"_42":95,"_44":96,"_46":47,"_48":311,"_50":51,"_52":371,"_53":373,"_55":374,"_375":31,"_57":31,"_9":376,"_63":31,"_64":377,"_66":378},"Stanford CS324: Large Language Models","

A comprehensive course dedicated specifically to LLMs, covering capabilities, harms, societal impact, training, scaling laws, and more. Still relatively new but draws on Stanford's expertise. A good academic complement to practical resources.

\n","missing",[61,209,315,316,317,318,319,320],"mlg_stanfordcslargelangu",[379],{"_53":324,"_117":380,"_119":101},"https://stanford-cs324.github.io/winter2022/","5e447a8029f22fdd7db0a58c44bdc3e8",{"_40":41,"_42":122,"_44":96,"_46":47,"_48":49,"_50":51,"_52":381,"_53":383,"_55":219,"_9":384,"_64":385,"_66":386},"Computer Vision: Algorithms and Applications",[61,62],"mlg_computervisionalgori",[387,389],{"_53":224,"_117":388,"_119":137},"https://szeliski.org/Book/",{"_53":135,"_117":390,"_119":137},"https://amzn.to/4ih70ni","72108181050bc7a7e4d0130604dd3ab9",{"_40":41,"_42":71,"_44":96,"_46":47,"_48":49,"_50":51,"_52":391,"_53":393,"_55":394,"_9":395,"_64":396,"_66":397},"Lilian Weng: \"What are Diffusion Models?\"","

A highly-regarded, comprehensive, and clear explanation of the theory and mathematics behind Denoising Diffusion Probabilistic Models (DDPMs). Excellent for building a solid conceptual understanding of how modern image generation works.

\n",[61,62],"mlg_lilianwengwhataredif",[398],{"_53":399,"_117":400,"_119":101},"Website:","https://lilianweng.github.io/posts/2021-07-11-diffusion-models/","6a52bd46a8ef05eabecc4113ce291235",{"_40":41,"_42":43,"_44":45,"_46":47,"_48":49,"_50":51,"_52":401,"_53":403,"_55":404,"_57":31,"_58":31,"_59":45,"_375":31,"_9":405,"_63":31,"_64":406,"_66":407},"Stanford CS231n: Deep Learning for Computer Vision","

The definitive academic course on deep learning for vision. Covers CNNs, object detection, segmentation, generation, and more. Known for excellent lectures and challenging assignments. Updated regularly. Visit the website for the most recent YouTube playlist; they record this every semester.

\n",[61,62],"mlg_stanfordcsndeeplearn",[408,410],{"_53":224,"_117":409,"_119":101},"http://cs231n.stanford.edu/index.html",{"_53":411,"_117":412,"_119":101},"YouTube (2018)","https://www.youtube.com/playlist?list=PL3FW7Lu3i5JvHM8ljYj-zLfQRF3EO8sYv","a6d9e6abf13c354ea849a29c02a3800d",{"_40":41,"_42":43,"_44":45,"_46":47,"_48":49,"_50":51,"_52":413,"_53":415,"_55":219,"_59":45,"_9":416,"_63":31,"_64":417,"_66":418},"Joseph Redmond CV + YOLO class",[61,62],"mlg_josephredmondcvyoloc",[419],{"_53":224,"_117":420,"_119":101},"https://pjreddie.com/courses/computer-vision/","86c183dea38d5eab21f1de9d2cee31c4",{"_40":94,"_42":122,"_44":96,"_46":47,"_48":423,"_50":51,"_52":421,"_53":424,"_55":425,"_9":426,"_64":427,"_66":428},"rl","Reinforcement Learning: An Introduction (2nd Ed.) by Sutton & Barto","

The undisputed bible of RL. Provides the foundational concepts, terminology, algorithms (MDPs, Monte Carlo, TD-Learning, Q-Learning, Policy Gradients), and theoretical underpinnings. Essential reading.

\n",[61,130],"mlg_reinforcementlearnin",[429,431],{"_53":149,"_117":430,"_119":101},"http://incompleteideas.net/book/the-book-2nd.html",{"_53":135,"_117":432,"_119":137},"https://amzn.to/4igJPJK","adf8207d359c7a8342b870e487349609",{"_40":41,"_42":43,"_44":96,"_46":47,"_48":423,"_50":51,"_52":433,"_53":435,"_55":436,"_57":31,"_58":31,"_59":45,"_9":437,"_64":438,"_66":439},"UC Berkeley CS285: Deep Reinforcement Learning","

The leading academic course focusing specifically on Deep RL (using neural networks within RL). Covers modern algorithms (DQN variations, Policy Gradients like TRPO/PPO, SAC, Model-Based RL) and theory. Taught by Sergey Levine, a top researcher.

\n",[61,130],"mlg_ucberkeleycsdeeprein",[440,442],{"_53":324,"_117":441,"_119":101},"http://rail.eecs.berkeley.edu/deeprlcourse/",{"_53":443,"_117":444,"_119":101},"YouTube (2022)","https://www.youtube.com/playlist?list=PL_iWQOsE6TfX7MaC6C3HcdOf1g337dlC9","7f3c7d78562057aada8468f476bea0e4",{"_40":94,"_42":122,"_44":96,"_46":47,"_48":423,"_50":51,"_52":445,"_53":447,"_55":219,"_9":448,"_63":31,"_64":449,"_66":450},"AI a Modern Approach",[104,61,209,130],"mlg_aiamodernapproach",[451,453],{"_53":224,"_117":452,"_119":101},"http://aima.cs.berkeley.edu/",{"_53":135,"_117":454,"_119":137},"https://amzn.to/3Y1J1RM","0113eb0d73f2331de2d6e1ae65798d0d",{"_40":41,"_42":43,"_44":96,"_46":47,"_48":423,"_50":51,"_52":455,"_53":457,"_55":219,"_59":161,"_57":31,"_58":31,"_9":458,"_63":31,"_64":459,"_66":460},"RL Course by David Silver",[61,130],"mlg_rlcoursebydavidsilve",[461],{"_53":255,"_117":462,"_119":101},"https://www.youtube.com/playlist?list=PLzuuYNsE1EZAXYR4FJ75jcJseBmo4KQ9-","5ac82f087ed786d7f6a40e9e6ecafd55",{"_40":70,"_42":122,"_44":45,"_46":47,"_48":124,"_50":51,"_52":463,"_53":465,"_55":466,"_9":467,"_64":468,"_66":469},"Python Crash Course, 3rd Edition","

Widely regarded as one of the best, most practical, and up-to-date introductions to Python for general purposes, making it a great starting point before specializing in data science libraries.

\n",[128,129],"mlg_pythoncrashcourserde",[470],{"_53":135,"_117":471,"_119":137},"https://amzn.to/4lGt6mf","006c6b755932efd55f6122a73caf33b4",{"_40":70,"_42":95,"_44":45,"_46":97,"_48":124,"_50":51,"_52":472,"_53":474,"_55":475,"_9":476,"_64":477,"_66":478},"Python for Everybody Specialization","

Extremely popular, well-structured introduction focusing on fundamentals. Available on Coursera and free via freeCodeCamp/Dr. Chuck's website. Less ML-specific than some later resources, but excellent for core Python.

\n",[128,129],"mlg_pythonforeverybodysp",[479],{"_53":116,"_117":480,"_119":101},"http://imp.i384100.net/Qj227Y","ef56f18aec424e9f5ee0b83e49458c03",{"_40":70,"_42":122,"_44":45,"_46":47,"_48":124,"_50":51,"_52":481,"_53":483,"_55":219,"_9":484,"_63":31,"_64":485,"_66":486},"Fluent Python: Clear, Concise, and Effective Programming 2nd Ed",[128,129],"mlg_fluentpythonclearcon",[487],{"_53":135,"_117":488,"_119":137},"https://amzn.to/4lzE10S","ad2b2af04c2eb91dceda738545e43a9b",{"_40":70,"_42":122,"_44":45,"_46":47,"_48":124,"_50":51,"_52":489,"_53":491,"_55":219,"_9":492,"_63":31,"_64":493,"_66":494},"Learning Python: Powerful Object-Oriented Programming 6th Edition",[128,129],"mlg_learningpythonpowerf",[495],{"_53":496,"_117":497,"_119":137},"Amazon:","https://amzn.to/4lAoJZQ","1852c00fa1076e0f01a273f23af3b154",{"_40":70,"_42":122,"_44":72,"_46":47,"_48":124,"_50":51,"_52":498,"_53":500,"_55":219,"_9":501,"_111":502,"_64":503,"_66":504},"Python for Data Analysis: Data Wrangling with Pandas, NumPy, and IPython 3rd Edition",[128,129],[104,106,107,145],"mlg_pythonfordataanalysi",[505,508],{"_53":506,"_117":507,"_119":101},"Webiste:","https://wesmckinney.com/book/",{"_53":135,"_117":509,"_119":137},"https://amzn.to/4juxt1G","5b061b3f4df7c9c690c9aaac07997da7",{"_40":41,"_42":122,"_44":45,"_46":47,"_48":124,"_50":51,"_52":510,"_53":512,"_55":513,"_9":514,"_111":515,"_64":519,"_66":520},"Designing Machine Learning Systems","

Quickly became the standard text for understanding the end-to-end process of building production ML systems. It's comprehensive, well-written, and covers the key challenges and patterns in a vendor-agnostic way (though uses examples from major platforms).

\n",[129],[108,109,110,516,209,517,316,317,518,129],"15","17","21","mlg_designingmachinelear",[521],{"_53":135,"_117":522,"_119":137},"https://amzn.to/3Gdv3q0","a81f3cd7f8c9acbeb1a828c8c34729f3",{"_40":41,"_42":95,"_44":45,"_46":97,"_48":124,"_50":51,"_52":523,"_53":525,"_55":526,"_9":527,"_111":530,"_64":531,"_66":532},"Machine Learning Engineering for Production Specialization","

Coursera + Andrew Ng, this specialization provides a structured, conceptual overview of the ML lifecycle, modeling pipelines, deployment strategies, and MLOps tools. Complements Chip Huyen's book well.

\n",[516,129,528,529],"27","28",[103,108,109,110,516,209,517,316,317,518,129],"mlg_machinelearningengin",[533],{"_53":116,"_117":534,"_119":101},"http://imp.i384100.net/jeJJYn","1c7e91cec7c7112fea9d155b7b649dec",{"_40":41,"_42":122,"_44":45,"_46":47,"_48":124,"_50":51,"_52":535,"_53":537,"_55":538,"_9":539,"_111":540,"_64":541,"_66":542},"Data Science on AWS: Implementing End-to-End, Continuous AI and Machine Learning Pipelines","

Eventually you'll be deploying your model to the cloud. Likely AWS. Better to get that mindset started early, you may even consider doing your development in the cloud (rather than localhost) to keep you eye on the ball.

\n",[129],[109,110,516,209,517,316,317,518,129],"mlg_datascienceonawsimpl",[543],{"_53":135,"_117":544,"_119":137},"https://amzn.to/3Ets4sT","9ce70976069f59895398039788eabd18",{"_40":70,"_42":43,"_44":72,"_46":47,"_48":124,"_50":51,"_52":545,"_53":547,"_55":219,"_59":161,"_58":31,"_9":548,"_111":549,"_64":550,"_66":551},"Amazon SageMaker Technical Deep Dive Series",[129],[110,516,209,517],"mlg_amazonsagemakertechn",[552],{"_53":255,"_117":553,"_119":101},"https://www.youtube.com/playlist?list=PLhr1KZpdzukcOr_6j_zmSrvYnLUtgqsZz","c30cb6bbddac551498a6e0077b23a3a3",{"_40":70,"_42":71,"_44":72,"_46":47,"_48":73,"_50":51,"_52":554,"_53":556,"_55":219,"_9":557,"_111":558,"_63":31,"_64":559,"_66":560},"aCloudGuru",[129],[110,516,209,517],"mlg_acloudguru",[561,564],{"_53":562,"_117":563,"_119":101},"Getting started tutorial","https://acloudguru.com/blog/engineering/which-aws-certification-should-i-take",{"_53":565,"_117":566,"_119":567},"Membership","https://acloudguru.com/pricing","$$$","5894302038f21ae05cc7f6b88678fbd8",{"_40":70,"_42":570,"_44":72,"_46":47,"_48":73,"_50":51,"_52":568,"_53":571,"_55":219,"_64":572,"_66":573},"podcast","MLG Episodes","mlg_mlgepisodes",[574,577,580],{"_53":575,"_117":576,"_119":101},"MLA 015 SageMaker 1","https://ocdevel.com/mlg/mla-15",{"_53":578,"_117":579,"_119":101},"MLA 016 SageMaker 2","https://ocdevel.com/mlg/mla-16",{"_53":581,"_117":582,"_119":101},"MLA 017 AWS Local Development","https://ocdevel.com/mlg/mla-17","067c3949c139818e535fd42d3ad43864",{"_40":70,"_42":71,"_44":45,"_46":47,"_48":141,"_50":51,"_52":583,"_53":585,"_55":586,"_9":587,"_64":588,"_66":589},"Math Primer PDF | Optional","

Fast primer. Skip to below if you're ready to dive in whole-sale, only read if you're knee-deep in ML and struggling with the math, need a quick-fix. See \"Section Notes\" of [cs229](http://cs229.stanford.edu/materials.html)

\n",[145],"mlg_mathprimerpdfoptiona",[590],{"_53":224,"_117":591,"_119":101},"http://cs229.stanford.edu/materials.html","2bc13e5748820384c3ce2939ef7cc806",{"_40":94,"_42":122,"_44":96,"_46":47,"_48":141,"_50":51,"_52":592,"_53":594,"_55":595,"_9":596,"_64":597,"_66":598},"Mathematics for Machine Learning","

Short and sweet textbook on ML math. Somewhere between a primer and the full deal. Highly lauded in the field.

\n",[145],"mlg_mathematicsformachin",[599],{"_53":224,"_117":600,"_119":101},"https://mml-book.github.io/","f651595ef05b41e0bdfeb5368a996fee",{"_40":41,"_42":43,"_44":96,"_46":47,"_48":141,"_50":51,"_52":601,"_53":603,"_55":219,"_206":31,"_59":161,"_58":31,"_9":604,"_64":605,"_66":606},"TGC - Mastering Linear Algebra: An Introduction with Applications",[145],"mlg_tgcmasteringlinearal",[607],{"_53":213,"_117":608,"_119":215},"https://thegreatcourses.7eer.net/c/358692/167386/2997?prodsku=1056&u=https%3A%2F%2Fwww.thegreatcourses.com%2Fcourses%2Fmastering-linear-algebra-an-introduction-to-applications&intsrc=PUI1_1204","7dc2f5e08f7bd73acf91d4ac6a141809",{"_40":41,"_42":95,"_44":96,"_46":97,"_48":141,"_50":51,"_52":609,"_53":611,"_55":219,"_9":612,"_111":613,"_64":614,"_66":615},"Fast.ai Linear Algebra",[145],[104,106],"mlg_fastailinearalgebra",[616,618],{"_53":224,"_117":617,"_119":101},"http://www.fast.ai/2017/07/17/num-lin-alg/",{"_53":255,"_117":619,"_119":101},"https://www.youtube.com/playlist?list=PLtmWHNX-gukIc92m1K0P6bIOnZb-mg0hY","2793adc4bfac0bde920472eca9c31f3d",{"_40":41,"_42":122,"_44":96,"_46":47,"_48":141,"_50":51,"_52":620,"_53":622,"_55":219,"_9":623,"_64":624,"_66":625},"Introduction to Linear Algebra",[145],"mlg_introductiontolinear",[626],{"_53":135,"_117":627,"_119":137},"https://amzn.to/3RhBJ8O","d48701356b8250dc846dfb1224aa5a29",{"_40":41,"_42":95,"_44":96,"_46":97,"_48":141,"_50":51,"_52":628,"_53":630,"_55":219,"_9":631,"_64":632,"_66":633},"KhanAcademy Linear Algebra",[145],"mlg_khanacademylinearalg",[634,636],{"_53":224,"_117":635,"_119":101},"https://www.khanacademy.org/math/linear-algebra",{"_53":255,"_117":637,"_119":101},"https://www.youtube.com/watch?v=xyAuNHPsq-g&list=PLFD0EB975BA0CC1E0","1a8d9d107b5679bc434fe3f2842b76d4",{"_40":41,"_42":43,"_44":96,"_46":47,"_48":141,"_50":51,"_52":638,"_53":640,"_55":219,"_206":31,"_59":161,"_58":31,"_9":641,"_64":642,"_66":643},"TGC Calculus",[145],"mlg_tgccalculus",[644,647,650],{"_53":645,"_117":646,"_119":215},"Calc 1 - Understanding Calculus: Problems, Solutions, and Tips","https://thegreatcourses.7eer.net/c/358692/167386/2997?prodsku=1007&u=https%3A%2F%2Fwww.thegreatcourses.com%2Fcourses%2Funderstanding-calculus-problems-solutions-and-tips&intsrc=PUI1_1204",{"_53":648,"_117":649,"_119":215},"Calc 2 - Understanding Calculus II: Problems, Solutions, and Tips","https://thegreatcourses.7eer.net/c/358692/167386/2997?prodsku=1018&u=https%3A%2F%2Fwww.thegreatcourses.com%2Fcourses%2Funderstanding-calculus-ii-problems-solutions-and-tips&intsrc=PUI1_1204",{"_53":651,"_117":652,"_119":215},"Calc 3 - Understanding Multivariable Calculus: Problems, Solutions, and Tips","https://thegreatcourses.7eer.net/c/358692/167386/2997?prodsku=1023&u=https%3A%2F%2Fwww.thegreatcourses.com%2Fcourses%2Funderstanding-multivariable-calculus-problems-solutions-and-tips&intsrc=PUI1_1204","2007c03993b86f381464f4cba28987fc",{"_40":41,"_42":43,"_44":96,"_46":47,"_48":141,"_50":51,"_52":653,"_53":655,"_55":219,"_59":161,"_58":31,"_9":656,"_64":657,"_66":658},"3Blue1Brown - Essence of calculus",[145],"mlg_bluebrownessenceofca",[659,662],{"_53":660,"_117":661,"_119":101},"YouTube - Basics","https://www.youtube.com/playlist?list=PLZHQObOWTQDMsr9K-rj53DwVRMYO3t5Yr",{"_53":663,"_117":664,"_119":101},"YouTube - Multivariate","https://www.youtube.com/watch?v=TrcCbdWwCBc&list=PLSQl0a2vh4HC5feHa6Rc5c0wbRTx56nF7","0e6a3527f173b515a31ad9e8b9376da2",{"_40":70,"_42":122,"_44":96,"_46":47,"_48":141,"_50":51,"_52":665,"_53":667,"_55":219,"_9":668,"_64":669,"_66":670},"Calculus Book",[145],"mlg_calculusbook",[671],{"_53":135,"_117":672,"_119":137},"https://amzn.to/3Y4e4wm","9ea86951fd84e4867ca68a73a0a462ae",{"_40":41,"_42":95,"_44":96,"_46":97,"_48":141,"_50":51,"_52":673,"_53":675,"_55":219,"_9":676,"_64":677,"_66":678},"KhanAcademy Calculus",[145],"mlg_khanacademycalculus",[679],{"_53":224,"_117":680,"_119":101},"https://www.khanacademy.org/math/calculus-home","a66e6dab61e9bc9c5c168ff3385c968f",{"_40":41,"_42":43,"_44":96,"_46":47,"_48":141,"_50":51,"_52":681,"_53":683,"_55":219,"_206":31,"_59":161,"_58":31,"_9":684,"_64":685,"_66":686},"TGC Statistics and Probability",[145,516],"mlg_tgcstatisticsandprob",[687,690],{"_53":688,"_117":689,"_119":215},"Learning Statistics: Concepts and Applications in R","https://thegreatcourses.7eer.net/c/358692/167386/2997?prodsku=1480&u=https%3A%2F%2Fwww.thegreatcourses.com%2Fcourses%2Flearning-statistics-concepts-and-applications-in-r&intsrc=PUI1_1204",{"_53":691,"_117":692,"_119":215},"What Are the Chances? Probability Made Clear","https://thegreatcourses.7eer.net/c/358692/167386/2997?prodsku=1474&u=https%3A%2F%2Fwww.thegreatcourses.com%2Fcourses%2Fwhat-are-the-chances-probability-made-clear&intsrc=PUI1_1204","0e680037c76b6a91c68990b0420b634e",{"_40":41,"_42":95,"_44":96,"_46":97,"_48":141,"_50":51,"_52":693,"_53":695,"_55":219,"_9":696,"_64":697,"_66":698},"KhanAcademy Statistics",[145,516],"mlg_khanacademystatistic",[699],{"_53":224,"_117":700,"_119":101},"https://www.khanacademy.org/math/statistics-probability","8505bad44112164393ce2b168276b0ec",{"_40":41,"_42":122,"_44":96,"_46":47,"_48":141,"_50":51,"_52":701,"_53":703,"_55":219,"_9":704,"_64":705,"_66":706},"All of statistics",[145,516],"mlg_allofstatistics",[707],{"_53":135,"_117":708,"_119":137},"https://amzn.to/4jlqCYY","a5a2f916ebadf3b91943094ad2f6edbd",{"_40":94,"_42":43,"_44":45,"_46":47,"_48":141,"_50":51,"_52":709,"_53":711,"_55":712,"_58":31,"_59":161,"_9":713,"_64":714,"_66":715},"StatQuest - Math","

StatQuest is very popular in the math & ML communities. There are multiple playlists for various topics, so I'll break out a few in their relevant locations in the resources subtrees.

\n",[145,516],"mlg_statquestmath",[716,717,720,723],{"_53":167,"_117":168,"_119":101},{"_53":718,"_117":719,"_119":101},"StatQuest main","https://www.youtube.com/playlist?list=PLblh5JKOoLUIcdlgu78MnlATeyx4cEVeR",{"_53":721,"_117":722,"_119":101},"Stats and ML","https://www.youtube.com/playlist?list=PLblh5JKOoLUJJpBNfk8_YadPwDTO2SCbx",{"_53":724,"_117":725,"_119":101},"Stats","https://www.youtube.com/playlist?list=PLblh5JKOoLUK0FLuzwntyYI10UQFUhsY9","9a50bbea2a94dd5884315a11c8712797",{"_40":41,"_42":71,"_44":96,"_46":47,"_48":73,"_50":51,"_52":726,"_53":728,"_55":729,"_206":31,"_59":161,"_58":31,"_9":730,"_64":731,"_66":732},"TGC Mathematical Decision Making","

Course on \"Operations Research\", similar to ML

\n",[105,109,516,528,529],"mlg_tgcmathematicaldecis",[733],{"_53":734,"_117":735,"_119":215},"Mathematical Decision Making: Predictive Models and Optimization","https://thegreatcourses.7eer.net/c/358692/167386/2997?prodsku=1342&u=https%3A%2F%2Fwww.thegreatcourses.com%2Fcourses%2Fmathematical-optimization-techniques&intsrc=PUI1_1204","b8135293b9324ec8ca2180e9c038a208",{"_40":41,"_42":43,"_44":96,"_46":47,"_48":141,"_50":51,"_52":736,"_53":738,"_55":219,"_206":31,"_59":161,"_58":31,"_9":739,"_64":740,"_66":741},"TGC Information Theory",[145,209],"mlg_tgcinformationtheory",[742],{"_53":743,"_117":744,"_119":215},"The Science of Information: From Language to Black Holes","https://thegreatcourses.7eer.net/c/358692/167386/2997?prodsku=1301&u=https%3A%2F%2Fwww.thegreatcourses.com%2Fcourses%2Fthe-science-of-information-from-language-to-black-holes&intsrc=PUI1_1204","f0263ed323248e73053721ca38127faf",{"_40":94,"_42":747,"_44":96,"_46":97,"_48":73,"_50":51,"_52":745,"_53":748,"_55":749,"_100":567,"_9":750,"_111":751,"_64":752,"_66":753},"degree","OMSCS","

Online Master of Science in Computer Science (OMSCS) - Georgia Institute of Technology. Launched in 2014, OMSCS remains arguably the pioneer and benchmark for affordable, rigorous, and reputable online Master's degrees in Computer Science from a top-tier university. It offers a Machine Learning specialization track alongside others (Computing Systems, Computational Perception & Robotics, Interactive Intelligence). Its low cost (~$7,000 total) combined with Georgia Tech's strong CS reputation makes it incredibly high value. While rigor is high and requires significant self-discipline (common to all online programs), its graduates are generally well-regarded. A CS degree provides broad, future-proof foundational knowledge, highly valued even for specialized ML/AI roles.

\n",[274],[103],"mlg_omscs",[754],{"_53":224,"_117":755,"_119":567},"https://www.omscs.gatech.edu/","5393844dbc06bc4ffce9742c30d61e08",{"_40":94,"_42":747,"_44":96,"_46":97,"_48":73,"_50":51,"_52":756,"_53":758,"_55":759,"_100":567,"_9":760,"_111":761,"_64":762,"_66":763},"MSCSO","

Online Master of Science in Computer Science (MSCSO) - The University of Texas at Austin. Launched a few years after OMSCS, UT Austin's MSCSO quickly established itself as a direct peer and top alternative. It offers a very similar model: affordable (~$10,000 total), fully online, rigorous coursework from a highly-ranked CS department. It also offers flexibility in course selection, allowing students to effectively create an AI/ML focus. It shares the benefits of a foundational CS degree. For many prospective students, the choice between OMSCS and MSCSO comes down to slight differences in course offerings, specific faculty, or application nuances. It's a near-equal contender for the top spot.

\n",[274],[103],"mlg_mscso",[764],{"_53":224,"_117":765,"_119":567},"https://cdso.utexas.edu/mscs","7f2943c46eee37332ad3e896c6b2564a",{"_40":41,"_42":747,"_44":96,"_46":97,"_48":73,"_50":51,"_52":766,"_53":768,"_55":219,"_100":567,"_9":769,"_262":31,"_63":31,"_64":770,"_66":771},"Udacity Machine Learning",[274],"mlg_udacitymachinelearni",[772],{"_53":773,"_117":774,"_119":567},"Udacity","https://www.udacity.com/course/machine-learning-engineer-nanodegree--nd009","4cd53d12488558af1cc13e946cdfc421",{"_40":41,"_42":747,"_44":96,"_46":97,"_48":423,"_50":51,"_52":775,"_53":777,"_55":219,"_100":567,"_9":778,"_262":31,"_63":31,"_64":779,"_66":780},"Udacity Artificial Intelligence",[274],"mlg_udacityartificialint",[781],{"_53":773,"_117":782,"_119":567},"https://www.udacity.com/ai","0cd6966308d92cc31d9995036f7a9653",{"_40":70,"_42":71,"_44":72,"_46":47,"_48":785,"_50":51,"_52":783,"_53":786,"_55":787,"_100":101,"_9":788,"_64":789,"_66":790},"fun","Wait But Why - The AI Revolution (2-Part Series)","

Although from 2015, Tim Urban's deep-dive articles (\"The Road to Superintelligence\" and \"Our Immortality or Extinction\") remain a uniquely accessible, engaging, and influential explanation of the core concepts of AI development stages (ANI, AGI, ASI), potential timelines, and existential implications. Fantastic starting point for grasping the big picture and why people talk about AI risk/reward.

\n",[208,209],"mlg_waitbutwhytheairevol",[791,794],{"_53":792,"_117":793,"_119":101},"Part 1","https://waitbutwhy.com/2015/01/artificial-intelligence-revolution-1.html",{"_53":795,"_117":796,"_119":101},"Part 2","https://waitbutwhy.com/2015/01/artificial-intelligence-revolution-2.html","0b2971645944c275eed0744862118a54",{"_40":41,"_42":799,"_44":72,"_46":47,"_48":785,"_50":51,"_52":797,"_53":801,"_55":802,"_58":31,"_100":137,"_64":803,"_66":804},[122,800],"audiobook","The Singularity Is Nearer","

Ray Kurzweil's 2024 follow-up to his seminal 2005 work. While The Singularity is Near popularized the concept, this updated version reflects recent advancements (LLMs, etc.) and refines his predictions (AGI by 2029, Singularity by 2045). Represents the techno-optimist viewpoint focused on human augmentation and exponential progress. Important for understanding this influential, albeit sometimes controversial, perspective. (Replaces the original The Singularity Is Near entry).

\n","mlg_thesingularityisnear",[805],{"_53":135,"_117":806,"_119":137},"https://amzn.to/3EbFg5H","78b62a20d13bee352475b4ae2a4157e7",{"_40":70,"_42":122,"_44":45,"_46":47,"_48":785,"_50":51,"_52":807,"_53":809,"_55":810,"_64":811,"_66":812},"The Quest for Artificial Intelligence","

A comprehensive academic history by Nils J. Nilsson, one of the pioneers in the field. While slightly dated (2009), it remains a standard reference for understanding the intellectual journey and key milestones before the deep learning explosion. Excellent for historical depth.

\n","mlg_thequestforartificia",[813,815],{"_53":149,"_117":814,"_119":101},"https://ai.stanford.edu/~nilsson/QAI/qai.pdf",{"_53":135,"_117":816,"_119":137},"https://amzn.to/4jgobGW","6d6a74f9c5a9467e68185e841766b5c8",{"_40":70,"_42":43,"_44":72,"_46":47,"_48":785,"_50":51,"_52":817,"_53":819,"_55":820,"_100":101,"_64":821,"_66":822},"AlphaGo - The Movie","

This documentary captures a pivotal moment in AI history – DeepMind's AlphaGo defeating world champion Lee Sedol. It's less a comprehensive history and more a deeply human story about a specific breakthrough that showcased the power of deep reinforcement learning and significantly shifted public perception of AI capabilities. Highly engaging and illustrative.

\n","mlg_alphagothemovie",[823],{"_53":255,"_117":824,"_119":101},"https://www.youtube.com/watch?v=WXuK6gekU1Y","9d57accced53ca0a1bf8d482f57c11fc",{"_40":70,"_42":827,"_44":72,"_46":47,"_48":785,"_50":51,"_52":825,"_53":828,"_55":829,"_58":31,"_64":830,"_66":831},[122,800],"Superintelligence: Paths, Dangers, Strategies","

Nick Bostrom's 2014 book remains the foundational text on the potential risks and strategic considerations of artificial superintelligence (ASI). It meticulously outlines the \"control problem\" and potential existential risks. Though challenging, it's essential for understanding the core arguments driving AI safety research and discourse, cited frequently by industry leaders. Still highly relevant in 2025.

\n","mlg_superintelligencepat",[832],{"_53":135,"_117":833,"_119":137},"https://amzn.to/3GfhlTt","7db2d2b00c90679f6bed3914c7863790",{"_40":70,"_42":836,"_44":72,"_46":47,"_48":785,"_50":51,"_52":834,"_53":837,"_55":838,"_58":31,"_64":839,"_66":840},[122,800],"The Coming Wave: Technology, Power, and the Twenty-First Century's Greatest Dilemma","

Written by Mustafa Suleyman (co-founder of DeepMind), this 2023 book offers a crucial, contemporary perspective from a leading AI pioneer. It examines the immense power and rapid proliferation of AI and synthetic biology, arguing for urgent containment strategies. Highly influential and provides an insider's view on the current wave of technology and its societal challenges. Excellent narration by the author in the audiobook.

\n","mlg_thecomingwavetechnol",[841],{"_53":135,"_117":842,"_119":137},"https://amzn.to/4jzwygz","21b0f813fee8555ac797c028f40e7f67",{"_40":70,"_42":845,"_44":72,"_46":47,"_48":785,"_50":51,"_52":843,"_53":846,"_55":847,"_58":31,"_64":848,"_66":849},[122,800],"Being You: A New Science of Consciousness","

Neuroscientist Anil Seth presents a compelling and accessible view of consciousness rooted in predictive processing and the brain as a \"prediction machine.\" Published in 2021, it's a highly-regarded contemporary take, moving beyond abstract philosophy towards a scientifically grounded understanding of subjective experience. Excellent for those curious about how minds (biological or potentially artificial) might arise.

\n","mlg_beingyouanewscienceo",[850],{"_53":135,"_117":851,"_119":137},"https://amzn.to/4jApz73","bda3a19fc840c10e9f9df5e54050da1f",{"_40":41,"_42":800,"_44":72,"_46":47,"_48":785,"_50":51,"_52":852,"_53":854,"_55":219,"_64":855,"_66":856},"TGC Philosophy of Mind: Brains, Consciousness, and Thinking Machines","mlg_tgcphilosophyofmindb",[857],{"_53":135,"_117":858,"_119":137},"https://amzn.to/3GcngJ3","8ca4bc4a0f0cd3ffccd662c16ab4d66d",{"_40":70,"_42":800,"_44":72,"_46":47,"_48":785,"_50":51,"_52":859,"_53":861,"_55":862,"_64":863,"_66":864},"TGC Mind-Body Philosophy","

Pretty similar to the other TGC above; just some more material, in case that one wasn't enough.

\n","mlg_tgcmindbodyphilosoph",[865],{"_53":135,"_117":866,"_119":137},"https://amzn.to/4cKWVOj","cc9bbb3c21833fa70830248168f15039",{"_40":41,"_42":869,"_44":45,"_46":47,"_48":785,"_50":51,"_52":867,"_53":870,"_55":871,"_58":31,"_9":872,"_63":31,"_64":873,"_66":874},[122,800],"The Master Algorithm","

Semi-technical overview of ML basics & main algorithms. Fun and learn at the same time! Archived: while good, its semi-technical overview might be better placed elsewhere or is slightly dated compared to the rapid pace of ML.

\n",[208],"mlg_themasteralgorithm",[875],{"_53":135,"_117":876,"_119":137},"https://amzn.to/3G70tOO","4f3cdc78d7162783b474711e76313432",{"_40":70,"_42":122,"_44":45,"_46":47,"_48":785,"_50":51,"_52":877,"_53":879,"_55":880,"_100":137,"_9":881,"_63":31,"_64":882,"_66":883},"The Society of Mind","

A classic (1986) by AI pioneer Marvin Minsky. Explores the idea that minds are composed of many smaller, simpler \"agents.\" While not reflecting modern neuroscience or ML techniques, its conceptual framework remains influential and offers a different perspective on intelligence and consciousness, particularly relevant to modularity in AI design. Important historical context from a founder. Archived: While a classic, it's less central to the current neuroscience/AI consciousness debate than Seth or Koch/IIT. Removed for slimness.

\n",[208,274],"mlg_thesocietyofmind",[884],{"_53":135,"_117":885,"_119":137},"https://amzn.to/43YFmIo","d68531d671b01d2e67b23794bf5e6055",{"_40":70,"_42":888,"_44":72,"_46":47,"_48":785,"_50":51,"_52":886,"_53":889,"_55":890,"_58":31,"_9":891,"_63":31,"_64":892,"_66":893},[122,800],"The Feeling of Life Itself: Why Consciousness Is Widespread but Can't Be Computed","

Christof Koch explains Integrated Information Theory (IIT), a prominent formal theory attempting to define and measure consciousness (Φ). Directly relevant to the AI consciousness debate, exploring whether machines could, in principle, possess the integrated information structure required for consciousness, even while arguing current architectures fall short. Key for understanding a major theoretical approach to AI consciousness.

\n",[208,274],"mlg_thefeelingoflifeitse",[894],{"_53":135,"_117":895,"_119":137},"https://amzn.to/3ROMjUO","a01c3a3183d09eb0d1ce1e17de28a373",{"_40":70,"_42":898,"_44":72,"_46":47,"_48":785,"_50":51,"_52":896,"_53":899,"_55":900,"_58":31,"_9":901,"_63":31,"_64":902,"_66":903},[122,800],"Machines of Loving Grace","

AI History. Archived: Good historical context, but Nilsson's book is more comprehensive for a deep dive, and AlphaGo documentary provides a more engaging snapshot of a key moment.

\n",[208],"mlg_machinesoflovinggrac",[904],{"_53":135,"_117":905,"_119":137},"https://amzn.to/3YwpNE2","2e05632a6f95ecaef30c58e305e6a96d",{"_40":70,"_42":908,"_44":72,"_46":47,"_48":785,"_50":51,"_52":906,"_53":909,"_55":910,"_58":31,"_9":911,"_63":31,"_64":912,"_66":913},[122,800],"How to Create a Mind: The Secret of Human Thought Revealed","

Archived: Kurzweil's newer book (Singularity is Nearer) is more current for his perspective.

\n",[208,274],"mlg_howtocreateamindthes",[914],{"_53":135,"_117":915,"_119":137},"https://amzn.to/4jb8hNR","38c596da089ddb8d9201857411192302",{"_40":94,"_42":570,"_44":45,"_46":47,"_48":918,"_50":51,"_52":916,"_53":15,"_55":919,"_9":920,"_64":921,"_66":922},[73,785],"

Teaches the fundamentals of ML in podcast form. Importantly, guides users to deep-dive the concepts offline via curated resources (this website!)

\n",[103],"mlg_machinelearningguide",[923],{"_53":224,"_117":17,"_119":101},"c38b7780a1ce13e0c443aef12843f0a7",{"_40":41,"_42":570,"_44":45,"_46":47,"_48":926,"_50":51,"_52":924,"_53":927,"_55":928,"_9":929,"_64":930,"_66":931},[73,785],"Machine Learning Street Talk (MLST)","

In-depth, technical discussions with leading AI experts, often dissecting research papers. Covers advanced AI research, diverse approaches (beyond just LLMs), cognitive science, neuroscience, and philosophy of mind. Rigorous and intellectually curious.

\n",[103],"mlg_machinelearningstree",[932,934,937],{"_53":255,"_117":933,"_119":101},"https://www.youtube.com/c/MachineLearningStreetTalk",{"_53":935,"_117":936,"_119":101},"iTunes","https://podcasts.apple.com/us/podcast/machine-learning-street-talk-mlst/id1510472996",{"_53":938,"_117":939,"_119":101},"Spotify","https://open.spotify.com/show/02e6PZeIOdpmBGT9THuzwR","94bc3ec6073666b750b4c026dd7d7d51",{"_40":41,"_42":570,"_44":72,"_46":47,"_48":942,"_50":51,"_52":940,"_53":943,"_55":944,"_9":945,"_64":946,"_66":947},[73,124],"Practical AI","

Makes AI practical, productive, and accessible. Discusses real-world use cases, implementations, and interviews experts, breaking down trends in an understandable way for application.

\n",[103],"mlg_practicalai",[948],{"_53":224,"_117":949,"_119":-7},"https://practicalai.fm/","404021e8871d010f6a519d72933502bd",{"_40":41,"_42":570,"_44":72,"_46":47,"_48":73,"_50":51,"_52":950,"_53":952,"_55":953,"_9":954,"_64":955,"_66":956},"Data Skeptic","

Explores topics in data science, statistics, machine learning, and AI, often applying critical thinking and skepticism. Features a mix of shorter \"mini-episodes\" explaining concepts and longer interviews with experts. Good for understanding core ideas and their real-world application and limitations.

\n",[103],"mlg_dataskeptic",[957],{"_53":224,"_117":958,"_119":101},"https://dataskeptic.com/","62b6e93ded0988545c396490094792f5",{"_40":70,"_42":570,"_44":72,"_46":47,"_48":961,"_50":51,"_52":959,"_53":962,"_55":963,"_9":964,"_64":965,"_66":966},"news_interviews","TWiML & AI","

Hosted by Sam Charrington, this podcast focuses on making ML and AI accessible through interviews with researchers, practitioners, and innovators. Covers a wide range of ML/AI topics including deep learning, NLP, MLOps, and industry trends. Great for staying current with technical advancements and applications.

\n",[103],"mlg_twimlai",[967],{"_53":224,"_117":968,"_119":101},"https://twimlai.com","1bec63ba4cd5bc16cc5c81f841491131",{"_40":41,"_42":570,"_44":72,"_46":47,"_48":961,"_50":51,"_52":969,"_53":971,"_55":972,"_64":973,"_66":974},"Lex Fridman Podcast","

Formerly focused heavily on AI, now broadened but still features many key figures in AI, technology, science, and philosophy. Excellent for long-form, deep conversations exploring the nature of intelligence, consciousness, and the future impact of technology. Highly inspirational.

\n","mlg_lexfridmanpodcast",[975],{"_53":224,"_117":976,"_119":101},"https://lexfridman.com/podcast/","794ce97ac3329b0700ca2c13dddca695",{"_40":70,"_42":570,"_44":72,"_46":47,"_48":73,"_50":51,"_52":977,"_53":979,"_55":980,"_64":981,"_66":982},"AWS Podcast","

Not ML proper, but AWS (or Azure, GCP, etc) will eventually be your bread-and-butter for training, tuning, deploying your models. AWS is the most popular of the cloud providers, especially in ML, so start familiarizing yourself with SageMaker, Batch, EMR, and all that good stuff.

\n","mlg_awspodcast",[983],{"_53":224,"_117":984,"_119":101},"https://aws.amazon.com/podcasts/aws-podcast/","20ce8abe6385dfd5a76173b1ce7554b3",{"_40":70,"_42":570,"_44":72,"_46":47,"_48":73,"_50":51,"_52":985,"_53":987,"_55":988,"_64":989,"_66":990},"Learning machines 101","

Last episode 2021. Less prominent now; structured courses are generally better for foundational learning via audio (just pocket your phone and ignore the video).

\n","mlg_learningmachines",[991],{"_53":224,"_117":992,"_119":101},"http://www.learningmachines101.com/","a4f1c0ddaeeda479fd9cd78419296c1f",{"_40":70,"_42":570,"_44":72,"_46":47,"_48":961,"_50":51,"_52":993,"_53":995,"_55":996,"_64":997,"_66":998},"Talking machines","

Last episode: 2021

\n","mlg_talkingmachines",[999],{"_53":224,"_117":1000,"_119":101},"http://www.thetalkingmachines.com/","48dc21f1ae54c51d87fff918327d3afb",{"_40":70,"_42":570,"_44":72,"_46":47,"_48":961,"_50":51,"_52":1001,"_53":1003,"_55":1004,"_64":1005,"_66":1006},"O'Reilly Data Show","

Last episode: 2019

\n","mlg_oreillydatashow",[1007],{"_53":224,"_117":1008,"_119":101},"https://www.oreilly.com/topics/oreilly-data-show-podcast","1550f2f6bca43eb2bd3a406f4c3aafc4",{"_40":41,"_42":570,"_44":72,"_46":47,"_48":73,"_50":51,"_52":1009,"_53":1011,"_55":1012,"_64":1013,"_66":1014},"Linear Digressions","

Last episode: 2020

\n","mlg_lineardigressions",[1015],{"_53":224,"_117":1016,"_119":101},"http://lineardigressions.com/","ee0943ac8a5241fcb957a5e4abadb26c",{"_40":70,"_42":570,"_44":72,"_46":47,"_48":73,"_50":51,"_52":1017,"_53":1019,"_55":1020,"_64":1021,"_66":1022},"Partially Derivative","

Last episode: 2017.

\n","mlg_partiallyderivative",[1023],{"_53":224,"_117":1024,"_119":101},"http://partiallyderivative.com/","52039e365b2da46849e0d2f5ddaa506c",{"_52":1025,"_53":1027,"_55":219,"_1028":1029,"_1030":1031},"Archive","pick","none","v",[1032],{"_52":257},"0fdba4106482e1113ff35cb29b5e09f6",{"_52":1033,"_53":1035,"_55":1036,"_1028":1037,"_1038":31,"_1030":1039},"Transformers / Large Language Models (LLMs)","

A subfield (or arguably, now a dominant paradigm) focusing on the Transformer architecture and its scaling to create powerful Large Language Models capable of diverse language (and increasingly, multi-modal) tasks. Primarily for NLP but increasingly multi-modal.

\n","any","expand",[1040,1041,1042],{"_52":342},{"_52":352},{"_52":362},"f84b57fb570b997da9156ac65ce49af0",{"_52":1043,"_53":1045,"_55":219,"_1028":1037,"_1030":1046},"More",[1047],{"_52":371},"c570d0c9ba03bb727b82d25c299b0dad",{"_52":1048,"_53":1050,"_55":1051,"_1028":1037,"_1038":31,"_1030":1052},"Generative Models (including Diffusion)","

Focus: Models designed to generate new data samples (images, text, audio) that resemble a learned distribution. Includes GANs, VAEs, and currently SOTA Diffusion models. Listed under CV for now, as Transformers (generative) are covered in LLMs (NLP); so what's left over is most popularly used in image generation.

\n",[1053,1054],{"_52":391},{"_52":38},"ea37b0b57bf1a5dff13f1b49444dc5fb",{"_52":1055,"_53":1045,"_55":219,"_1028":1037,"_1030":1057},[1058,1059],{"_52":401},{"_52":413},"04131e1660d157f33487cf10f69d53bd",{"_52":1060,"_53":1045,"_55":219,"_1028":1037,"_1030":1062},[1063,1064],{"_52":445},{"_52":455},"d3a53b4950a1001d001443f33969b703",{"_52":1065,"_53":1067,"_55":1068,"_1028":1069,"_1030":1070},"Alternatives","

These are popular books, but >1000 pages. Since you have a lot of territory to cover in ML, only pick one of these if you're really serious about becoming a Python pro. My opinion: the basics (above resources) will suffice, and you'll learn as you go along.

\n","one",[1071,1072],{"_52":481},{"_52":489},"3be54c5ed2eb97db0ed952fc8154492d",{"_52":1073,"_53":1075,"_55":1076,"_1028":1037,"_1030":1077},"AWS-Specific","

Rather than writing your own server-code with FastAPI (the traditional ML deployment path), learn AWS nuts-to-bolts. They offer not only hosted server modules (like auth via Cognito, storage via S3, and security via IAM / VPC) - but also the full end-to-end machine learning data-prep, training, and deployment lifecycle. I loved aCloudGuru, but my company paid the hefty subscription fee. Follow the certification paths, even if you don't take the cert tests.

\n",[1078,1079,1080,1081],{"_52":535},{"_52":545},{"_52":554},{"_52":568},"65c982dcade20b3d6234ffc398704061",{"_52":1082,"_53":1084,"_55":219,"_1028":1069,"_1030":1085},"Linear Algebra",[1086,1087,1088,1089],{"_52":601},{"_52":609},{"_52":620},{"_52":628},"b5818dcaed615c501fe825a2d4944199",{"_52":1090,"_53":1092,"_55":219,"_1028":1069,"_1030":1093},"Calculus",[1094,1095,1096,1097],{"_52":638},{"_52":653},{"_52":665},{"_52":673},"b1d7a7ef827a855fd33e597f785c5244",{"_52":1098,"_53":1100,"_55":219,"_1028":1069,"_1030":1101},"Statistics & Probability",[1102,1103,1104],{"_52":681},{"_52":693},{"_52":701},"33951db93c96a5f0749d47f121938164",{"_52":1105,"_53":1107,"_55":1108,"_1028":1037,"_1030":1109},"Other","

Misc topics valuable to ML, but not the core triumvirate

\n",[1110,1111,1112],{"_52":709},{"_52":726},{"_52":736},"626a113bdde4f4468b3eeaaecb06d360",{"_52":1113,"_53":1115,"_55":219,"_1028":1029,"_1030":1116},"Udacity Nanodegrees",[1117,1118],{"_52":766},{"_52":775},"a430333b4e0441a7aea6aed272f8682c",{"_52":1119,"_53":1121,"_55":219,"_1028":1037,"_1038":31,"_9":1122,"_1030":1123},"Big Picture & Engaging Introductions",[208],[1124,1125],{"_52":783},{"_52":797},"9bbc7b5a4994e07854998400713a7d60",{"_52":1126,"_53":1128,"_55":219,"_1028":1037,"_1038":31,"_9":1129,"_1030":1130},"History of AI",[208],[1131,1132],{"_52":807},{"_52":817},"33b2b150722386a796f86f328ae9439c",{"_52":1133,"_53":1135,"_55":219,"_1028":1037,"_1038":31,"_9":1136,"_1030":1137},"Future, Risk & Societal Impact",[208],[1138,1139],{"_52":825},{"_52":834},"a3d587eadf34ea0729358de15f67d6df",{"_52":1140,"_53":1142,"_55":1143,"_1028":1037,"_9":1144,"_1038":31,"_1030":1145},"Consciousness & Mind","

Great discussions on what consciousness is, and if/how AI can achieve it.

\n",[208,209],[1146,1147,1148],{"_52":843},{"_52":852},{"_52":859},"bd92af5f4f6ded9893c3251b2916d6ef",{"_52":1149,"_53":1045,"_55":1151,"_1028":1037,"_1030":1152},"

These are still fun reads, but they're slightly dated, and I want to keep the syllabus slim. So if you chewed through all of the above, by all means - continue!

\n",[1153,1154,1155,1156,1157],{"_52":867},{"_52":877},{"_52":886},{"_52":896},{"_52":906},"7144d5fe5157e0f1507d2c901bd1f5fd",{"_52":1158,"_53":1045,"_55":1160,"_1028":1037,"_1030":1161},"

Still active and valuable, but nesting here to keep the core list slim.

\n",[1162,1163,1164],{"_52":969},{"_52":86},{"_52":977},"c9584c444ef84021ab433ee55af03232",{"_52":1165,"_53":1167,"_55":1168,"_1028":1037,"_1030":1169},"Inactive","

These podcasts no longer appear active. If you're less concerned about cutting-edge, these will still hold high catch-up value.

\n",[1170,1171,1172,1173,1174],{"_52":985},{"_52":993},{"_52":1001},{"_52":1009},{"_52":1017},"68784899adb3d3939553b557af20e1b7",{"_52":1175,"_53":1045,"_55":1177,"_1028":1037,"_1030":1178},"

And so much more! Below are super valuable must-reads, you'll want them eventually. But you're probably hungry to move on to deep learning - so feel free to revisit.

\n",[1179,1180,1181,1182,1183,1184],{"_52":202},{"_52":216},{"_52":228},{"_52":237},{"_52":247},{"_52":1025},"cd2cd5278126455b30f40d7bb92cbe77",{"_52":1185,"_53":1187,"_55":1188,"_1028":1037,"_1030":1189},"Natural Language Processing (NLP), Transformers, LLMs","

Focuses on enabling computers to understand, process, and generate human language. This field has been revolutionized by Transformers.

\n",[1190,1191,1192,1193],{"_52":309},{"_52":329},{"_52":1033},{"_52":1043},"88626773913c25437628b1480f074350",{"_52":1194,"_53":1196,"_55":1197,"_1028":1037,"_1030":1198},"Computer Vision (CV), Generative Models, Diffusion","

Focus: Enabling computers to \"see\" and interpret information from images and videos (recognition, detection, segmentation, generation).

\n",[1199,1200,1201],{"_52":381},{"_52":1048},{"_52":1055},"77c7e7845deef04890cf4038a723fd19",{"_52":1202,"_53":1204,"_55":1205,"_1028":1037,"_1030":1206},"Reinforcement Learning (RL)","

Focus: Training agents to make sequences of decisions in an environment to maximize cumulative reward. Used in games, robotics, optimization.

\n",[1207,1208,1209],{"_52":421},{"_52":433},{"_52":1060},"5e0a32362f4681ddcf9b8a524af0d4a2",{"_52":1210,"_53":1212,"_55":219,"_1028":1069,"_1038":31,"_1030":1213},"Python",[1214,1215,1216],{"_52":463},{"_52":472},{"_52":1065},"2b620791a6b9596951467113d5944c32",{"_52":1217,"_53":1219,"_55":1220,"_1028":1037,"_1038":31,"_1030":1221},"MLOps & Deployment","

Understanding how to operationalize ML models (MLOps) is crucial. Start with the concepts, then dive into platform specifics (using AWS as the primary example).

\n",[1222,1223,1224],{"_52":510},{"_52":523},{"_52":1073},"3c29387dabdf8060375b7b556995a6ab",{"_52":1225,"_53":1227,"_55":1228,"_1028":1229,"_1038":31,"_9":1230,"_1030":1231},"Math","

Self-taught ML math learning track - 25% of your learning time

\n","ordered",[145],[1232,1233,1234,1235,1236,1237],{"_52":583},{"_52":592},{"_52":1082},{"_52":1090},{"_52":1098},{"_52":1105},"ffa98b5dd5d76d6bcabfb00e5e9526cd",{"_52":1238,"_53":1240,"_55":1241,"_1028":1229,"_1030":1242},"Certificates","

While the certificate market has become saturated since 2017, and no certificate carries the weight of a reputable Master's degree as a formal credential for securing top-tier ML/AI roles, certain programs excel at delivering foundational knowledge. The primary strength of certificates like Andrew Ng's highly-regarded Machine Learning and Deep Learning Specializations lies not in the credential itself for job hunting, but in the quality, structure, and recognition of the education provided by a leading figure. They form an essential learning path for self-starters needing to grasp core concepts. While many other certificates exist (e.g., platform or framework-specific), these DeepLearning.AI specializations remain the most universally recognized choices for demonstrating foundational ML and DL understanding.

\n",[1243,1244,1245],{"_52":92},{"_52":268},{"_52":1113},"d2a8fbf131a54416b574445cf1e00fe4",{"_52":1246,"_53":1248,"_55":1249,"_1028":1037,"_1030":1250},"Inspiration, History, Philosophy","

Non-technical machine learning & AI content: introduction to the subject, inspiration, history, or philosophy. Great for downtime or diversifying your understanding beyond pure technicals.

\n",[1251,1252,1253,1254,1255],{"_52":1119},{"_52":1126},{"_52":1133},{"_52":1140},{"_52":1149},"345feb3838f90acc48a6cdf2644375e9",{"_52":1256,"_53":1258,"_55":1259,"_1028":1037,"_1038":31,"_1030":1260},"Podcasts","

Once you've gotten your fill of the above resources, time to go into auto-pilot. Try a few of these podcasts, find your favorites, and coast.

\n",[1261,1262,1263,1264,1265,1266,1267],{"_52":916},{"_52":924},{"_52":940},{"_52":950},{"_52":959},{"_52":1158},{"_52":1165},"c8b6b936b6ef102ca17efce2a8b70171",{"_52":1268,"_53":1270,"_55":1271,"_1028":1272,"_1038":31,"_1030":1273},"Basics","

Machine learning Basics. Let the games begin!

\n","all",[1274,1275,1276,1277,1278],{"_52":92},{"_52":120},{"_52":138},{"_52":157},{"_52":1175},"15952a5bccd9695ddca7d78639278858",{"_52":1279,"_53":1281,"_55":1282,"_1028":1037,"_1038":31,"_1030":1283},"DL Topics (NLP, CV, RL)","

Within deep learning, you'll eventually want to specialize. While exposure to multiple areas is beneficial, focusing on mastering one area initially is often a good strategy. Choose one of the following subfields to dive deeper into.

\n",[1284,1285,1286,1287],{"_52":1185},{"_52":1194},{"_52":1202},{"_52":68},"6c6918337c85932224877fdc0a45fda0",{"_52":1288,"_53":1290,"_55":1291,"_1028":1037,"_1038":31,"_1030":1292},"Programming","

Python is the lingua franca of machine learning. You need a solid foundation. Choose ONE resource to learn the core language.

Scikit-learn as your shallow-learning library
Tensorflow or PyTorch as your deep-learning framework (prefer PyTorch)
Numpy Pandas, and Jupyter as your utility belt

\n",[1293,1294,1295,1296],{"_52":1210},{"_52":120},{"_52":498},{"_52":280},"c73b2439a40485940c80708d089f1a3d",{"_52":1297,"_53":1299,"_55":1300,"_1028":1069,"_1038":31,"_1030":1301},"Degrees / Certificates","

Choosing a formal degree path is a significant commitment and replaces the need for a curated self-study path. Choose this if you seek a formal, structured, and credentialed education recognized by employers. This section focuses on the most reputable and cost-effective online options. This section focuses on the most reputable and cost-effective online options.

\n",[1302,1303,1304,1305],{"_52":745},{"_52":756},{"_52":80},{"_52":1238},"526f624500d87c040cdacfbf1cd0140c",{"_52":1306,"_53":1308,"_55":1309,"_1028":1037,"_1038":31,"_1030":1310},"Fun","

Mostly non-technical, supplementary audio for driving / chores / and exercise, or books for leisure learning.

\n",[1311,1312],{"_52":1246},{"_52":1256},"29c3db2b515e543d3e530e3803192829",{"_52":1313,"_53":1315,"_55":219,"_1028":1069,"_1038":31,"_1030":1316},"Deep Learning",[1317,1318,1319,1320],{"_52":268},{"_52":280},{"_52":297},{"_52":1279},"889991e0c3314374d9af8d097d437675",{"_52":1321,"_53":1323,"_55":1324,"_1028":1037,"_1030":1325},"Technology","

This section covers the essential tools and practices for building, training, and deploying machine learning models. We focus on Python, the core data science libraries, and the fundamentals of MLOps, primarily using AWS as the example cloud provider due to its market dominance.

\n",[1326,1327],{"_52":1288},{"_52":1217},"380a851fedd69d22a9aa0dc44e6178bf",{"_52":1328,"_53":170,"_55":1330,"_1028":1229,"_1038":31,"_1030":1331},"

Self-taught ML main track - 75% of your learning time.

\n",[1332,1333,1334],{"_52":1268},{"_52":1313},{"_52":1321},"top",[],"nids",[],{"_14":15,"_16":17,"_18":19,"_20":21,"_22":23,"_24":1340,"_26":27,"_28":29,"_30":31},["D",1485932400000],"episode",{"_9":31,"_52":1343,"_262":31,"_1344":1345,"_1341":1343,"_1346":1347,"_1354":1355,"_1356":1357,"_1358":1343,"_26":1359,"_14":1360},11,"created","2017-03-08","file",{"_1348":1349,"_1350":1351,"_1352":1353},"url","http://ocdevel.com/files/podcasts/machine-learning/ml-11.mp3","length",6946229,"duration","7:45","guid","fe205bbc-b9d4-4df5-b840-c6f5b728903f","libsynEpisode",5440747,"mergeEpisode","Checkpoint - start learning the material offline!","Checkpoint","transcript","i","root","mlg.11","actionData","errors"]