AASDL Program
November 5th: Ian Goodfellow
Morning, 9:00-11:00 Intro to Deep Learning
- Maximum likelihood
- Stochastic gradient descent
- Deep architectures
- Backpropagation
- LSTMs
Morning, 11:30-14:00: Computer Vision
- Convolution
- Pooling
- Maxout
- Network-in-network
- Inception
- Batch normalization
- Image captioning
Afternoon, 15:00-17:00: Intro to Theano, computer vision exercises
November 6th: Navdeep Jaitly
Morning, 9:00-11:00
- The hybrid model for speech recognition
- DNN based acoustic models
- LSTM based acoustic models
- Recent developments in end to end speech recognition
Afternoon, 11:30-14:00
- Building and training a basic DNN based acoustic model
- Building a recognizer in Theano
Afternoon, 15:00-17:00: Speech recognition exercises
Closing