The recommended readings for this course are freely available online and are as follows:
| Date | Topics | Assigned Readings for Class | Assignments Due Before Class (posted on Canvas) |
|---|---|---|---|
| Mon, Aug 22 | Course introduction (lecture slides) |
||
| Wed, Aug 24 | Artificial neurons (lecture slides) |
Ch. 1 of Goodfellow book, Ch. 1-2.5 and 4-4.2 of Kamath book | |
| Mon, Aug 29 | Feedforward neural networks (lecture slides) |
Ch. 6-6.4 of Goodfellow book | Problem set 1 |
| Wed, Aug 31 | Gradient descent and training neural networks (lecture slides) |
Ch. 4-5.1, 5.9-5.10, and 6.5-6.6 of Goodfellow book, Ch. 4.3-4.42 of Kamath book | |
| Mon, Sep 5 | No class (Labor day holiday) | ||
| Wed, Sep 7 | Neural network training (lecture slides) |
Ch. 5.2-5.6, 5.11, 8-8.6 of Goodfellow book, Ch. 4.4.3 of Kamath book | |
| Mon, Sep 12 | Convolutional neural networks (lecture slides) |
Ch. 9-9.5 and 9.10-9.11 of Goodfellow book, (Optional) Ch. 6-6.3 of Kamath book | Lab assignment 1 |
| Wed, Sep 14 | Introduction to computer vision, image classification (lecture slides) |
Ch. 12.2 of Goodfellow book, Ch. 6.5-6.6 of Kamath book | |
| Mon, Sep 19 | Regularization (lecture slides) |
Ch. 7 of Goodfellow book, Ch. 4.5 of Kamath book | Problem set 2 |
| Wed, Sep 21 | Pretrained CNN features and fine-tuning (lecture slides) |
Ch. 12-12.1 of Goodfellow book | |
| Mon, Sep 26 | Object detection and semantic segmentation (lecture slides) |
Ch. 9.6-9.7 of Goodfellow book, Faster R-CNN, Fully Convolutional Networks for Semantic Segmentation | |
| Wed, Sep 28 | Recurrent neural networks (lecture slides) |
Ch. 10 of Goodfellow book, (Optional) Ch. 7.1-7.4 of Kamath book | Lab assignment 2 |
| Mon, Oct 3 | Introduction to natural language processing, neural word embeddings (lecture slides) |
Ch. 12.4 of Goodfellow book, Ch. 5.1-5.5 of Kamath book | |
| Wed, Oct 5 | Introduction to attention (lecture slides) |
Ch. 7.5 and 9-9.2.5 of Kamath book | |
| Mon, Oct 10 | Transformers (lecture slides) |
Ch. 9.2.6-9.2.10 of Kamath book | Lab assignment 3 |
| Wed, Oct 12 | Popular transformers (lecture slides) |
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding | |
| Mon, Oct 17 | Multimodal neural networks: visual question answering (lecture slides) |
LXMERT: Learning Cross-Modality Encoder Representations from Transformers | Problem set 3 |
| Wed, Oct 19 | Multimodal neural networks: image captioning (lecture slides) |
Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks | |
| Mon, Oct 24 | Multimodal neural networks: visual dialog (lecture slides) |
||
| Wed, Oct 26 | Self-supervised learning and GANs (lecture slides) |
Ch. 4.6 and 10-10.3 of Kamath book | Lab assignment 4 |
| Mon, Oct 31 | Few/zero shot learning (lecture slides) |
Ch. 10.4-11.2 of Kamath book | |
| Wed, Nov 2 | Responsible/ethical deep learning (lecture slides) |
||
| Mon, Nov 7 | Deep learning in industry (Guest speaker: Sharath Cholleti) |
Final project proposal | |
| Wed, Nov 9 | Deep learning in industry (Guest speaker: Lucas Hayne, Senior PhD Student) |
||
| Mon, Nov 14 | Deep learning in industry (Guest speaker: Mehrnoosh Sameki, Microsoft) |
||
| Wed, Nov 16 | Deep learning for speech processing and information retrieval (lecture slides) |
Final project outline | |
| Mon, Nov 21 | No class (Fall break) | ||
| Wed, Nov 23 | No class (Fall break) | ||
| Mon, Nov 28 | Model compression (lecture slides) |
||
| Wed, Nov 30 | Efficient learning (lecture slides) |
||
| Mon, Dec 5 | Deep reinforcement learning (lecture slides) |
Final project presentation | |
| Wed, Dec 7 | Course finale | ||
| Tue, Dec 13 | No class (final exam week) | Final project report |