1/16 |
History of Deep Learning |
Goodfellow Ch. 1-5 |
1/23 |
Introduction to Pytorch |
Goodfellow Ch. 6
Original UAF Paper
Depth vs. Width (Theorem 1)
|
1/28 |
Introduction to Neural Networks |
Goodfellow Ch. 7-8
Literature Review
|
1/30 |
Challenges in Training Neural Nets |
Goodfellow Ch. 7-8 |
2/4 |
Deep Vs. Shallow Learning |
Goodfellow Ch. 9
Do Deep Nets Really Need to be Deep
Deep vs. Shallow Complexity
No-Flattening
Depth vs. Width (Theorem 7)
|
2/6 |
Convolutional Neural Nets |
Goodfellow Ch. 9 |
2/11 |
CNNs and Capsule Nets |
Goodfellow Ch. 20
Dynamic Routing
|
2/13 |
Problems with CNNs and recent innovations |
Goodfellow Ch. 20 |
2/18 |
Vector semantics and CNNs for NLP |
Goodfellow Ch. 20 |
2/25 |
Autoencoders |
Goodfellow Ch. 20 |
2/27 |
GANs |
Goodfellow Ch. 20 |
3/11 |
RNNs and LSTMs |
Goodfellow Ch. 10
The Unreasonable Effectiveness of Recurrent Neural Networks
|
3/13 |
Generative RNNs |
|
3/18 |
Attention |
Neural Machine Translation by Jointly Learning to Align and Translate
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
Grammar as a Foreign Language
Teaching Machines to Read and Comprehend
|
3/20 |
Attention and Transformers |
|
3/25 |
Reinforcement Learning, Part I |
|
4/01 |
Hyperparameters and learning to learn |
|
4/08 |
Neuroscience, Part I |
|
4/10 |
Neuroscience, Part II |
|
4/15 |
Deep Learning & Society |
|
4/17 |
Applications of Deep Learning |
|
4/24 |
Sarcasm Presentation |
|