Machine Learning Guide
A machine learning podcast teaching the fundamentals of machine learning and artificial intelligence. It covers intuition, models, neural networks, math, languages, frameworks, etc. Where visual ML resources provide the trees, I provide the forest. Podcasts are a great supplement during exercise, commute, chores, etc.
MLG 023 Deep NLP 2
Aug 20, 2017
Click to Play Episode
RNN review, bi-directional RNNs, LSTM & GRU cells.
Try a walking desk to stay healthy while you study or work!
Resources
Resources best viewed here
Speech and Language Processing
Natural Language Processing - Stanford University
CS224N: Natural Language Processing with Deep Learning | Winter 2019
Show Notes
See resources on Deep Learning episode.
RNN Review
- Vanilla: When words + running context is sufficient.
- POS, NER, stocks, weather
- Bidirectional RNN (BiLSTM): When stuff from right helps too
- Encoder/decoder or Seq2seq: When you should hear everything first / spin a different way
- Classification, sentiment, translation
- Now w/ word embeddings
Train: backprop through time
- Vanishing/exploding gradient
- ReLU vs Sigmoid vs TanH (Nonlinearities future episode)
- Forget gate layer
- Input gate layer: decides which values to update
- Tanh layer: creates new candidate values
- Output layer