MLG 025 Convolutional Neural Networks
Oct 30, 2017
Click to Play Episode

Convnets or CNNs. Filters, feature maps, window/stride/padding, max-pooling.

Resources
Resources best viewed here
Stanford CS231n: Convolutional Neural Networks for Visual Recognition
Computer Vision: Algorithms and Applications
Joseph Redmond CV + YOLO class
Show Notes

See resources on Deep Learning episode.

  • One-time donations w/ BTC / PayPal
  • Image recognition, classification - computer vision
    • ML takeover
    • Final main network (MLP, RNN, CNN)
  • Don't use MLP for images, use CNNs
  • Filters -> feature maps -> convolutional layers
  • Window, stride, padding
  • Max-pooling
  • Architectures (ILSVRC ImageNet Challenge)
    • LeNet-5
    • AlexNet
    • GoogLeNet
    • Inception
    • Resnet
    • etc..