CS 230 ― Deep Learning

My twin brother Afshine and I created this set of illustrated Deep Learning cheatsheets covering the content of the CS 230 class, which I TA-ed in Winter 2019 at Stanford. They can (hopefully!) be useful to all future students of this course as well as to anyone else interested in Deep Learning.

Convolutional Neural Networks
  • • Types of layer, filter hyperparameters, activation functions
  • • Object detection, face verification and recognition
  • • Neural style transfer, architectures using computational tricks
Recurrent Neural Networks
  • • Vanishing/exploding gradient, GRU, LSTM, variants of RNNs
  • • Word2vec, skip-gram, negative sampling, GloVe, attention model
  • • Language model, beam search, Bleu score
Deep Learning tips and tricks
  • • Data augmentation, batch normalization, regularization
  • • Xavier initialization, transfert learning, adaptive learning rates
  • • Overfitting small batch, gradient checking

Would you like to see this set of cheatsheets in your native language? You can help us translating them on GitHub!