Difference between revisions of "Winter 2021 CS291A Syllabus"
From courses
| (20 intermediate revisions by the same user not shown) | |||
| Line 1: | Line 1: | ||
| + | Checkout the class presentation schedule for additional readings: | ||
| + | [https://docs.google.com/spreadsheets/d/1p0M7X9OZwcRHT4OhxX3snGjskfltUG-uFIL0T6rLjK8/edit?usp=sharing Class Presentation Schedule] | ||
| + | |||
*1/4 Introduction, logistics, and deep learning. | *1/4 Introduction, logistics, and deep learning. | ||
*1/6 Tips for a successful class project | *1/6 Tips for a successful class project | ||
*1/11 Neural network basics, & backpropagation | *1/11 Neural network basics, & backpropagation | ||
| − | *1/13 Word embeddings (Project proposal due [https://forms.gle/TjYSjc5iE1Zm24ED8 submission link], HW1 out) | + | *1/13 Word embeddings (Project proposal due 23:59PT 1/13 [https://forms.gle/TjYSjc5iE1Zm24ED8 submission link], HW1 out) |
** [https://www.aclweb.org/anthology/Q17-1010/ Enriching Word Vectors with Subword Information] | ** [https://www.aclweb.org/anthology/Q17-1010/ Enriching Word Vectors with Subword Information] | ||
** [https://www.aclweb.org/anthology/C18-1139/ Contextual String Embeddings for Sequence Labeling] | ** [https://www.aclweb.org/anthology/C18-1139/ Contextual String Embeddings for Sequence Labeling] | ||
| − | + | *1/18 NO CLASS (University Holiday: Martin Luther King Jr. Day) | |
| − | *1/18 University Holiday: Martin Luther King Jr. Day | ||
*1/20 RNNs | *1/20 RNNs | ||
** [http://www.fit.vutbr.cz/research/groups/speech/publi/2010/mikolov_interspeech2010_IS100722.pdf Recurrent neural network based language model] | ** [http://www.fit.vutbr.cz/research/groups/speech/publi/2010/mikolov_interspeech2010_IS100722.pdf Recurrent neural network based language model] | ||
| + | ** [https://arxiv.org/abs/1502.03240 Conditional Random Fields as Recurrent Neural Networks] | ||
*1/25 LSTMs/GRUs | *1/25 LSTMs/GRUs | ||
** [https://arxiv.org/pdf/1802.05365.pdf Deep contextualized word representations] | ** [https://arxiv.org/pdf/1802.05365.pdf Deep contextualized word representations] | ||
| − | ** [https://arxiv.org/pdf/ | + | ** [https://arxiv.org/pdf/1410.3916.pdf Memory Networks] |
*1/27 Sequence-to-sequence models | *1/27 Sequence-to-sequence models | ||
| + | ** [https://www.aclweb.org/anthology/N19-4009/ fairseq: A Fast, Extensible Toolkit for Sequence Modeling] | ||
| + | ** [https://arxiv.org/abs/1511.06732 Sequence Level Training with Recurrent Neural Networks] | ||
*2/1 Convolutional Neural Networks (HW1 due and HW2 out) | *2/1 Convolutional Neural Networks (HW1 due and HW2 out) | ||
| − | ** [https://www.nature.com/articles/s41586-019-1923-7 Improved protein structure prediction using potentials from deep learning] | + | ** [https://arxiv.org/abs/1608.06993 Densely Connected Convolutional Networks] |
| + | ** [https://www.nature.com/articles/s41586-019-1923-7 Improved protein structure prediction using potentials from deep learning] | ||
*2/3 Attention mechanisms | *2/3 Attention mechanisms | ||
| + | ** [https://www.aclweb.org/anthology/D15-1044.pdf A Neural Attention Model for Sentence Summarization] | ||
| + | ** [https://arxiv.org/abs/1409.0473 Neural Machine Translation by Jointly Learning to Align and Translate] | ||
*2/8 Transformer and BERT (Mid-term report due [https://forms.gle/3mLA46FANTDZ5s5FA submission link]) | *2/8 Transformer and BERT (Mid-term report due [https://forms.gle/3mLA46FANTDZ5s5FA submission link]) | ||
** [https://arxiv.org/abs/1906.08237 XLNet: Generalized Autoregressive Pretraining for Language Understanding] | ** [https://arxiv.org/abs/1906.08237 XLNet: Generalized Autoregressive Pretraining for Language Understanding] | ||
** [https://arxiv.org/abs/1907.11692 RoBERTa: A Robustly Optimized BERT Pretraining Approach] | ** [https://arxiv.org/abs/1907.11692 RoBERTa: A Robustly Optimized BERT Pretraining Approach] | ||
** [https://arxiv.org/abs/1909.11942 ALBERT: A Lite BERT for Self-supervised Learning of Language Representations] | ** [https://arxiv.org/abs/1909.11942 ALBERT: A Lite BERT for Self-supervised Learning of Language Representations] | ||
| − | *2/10 Mid-term project updates | + | *2/10 Mid-term project updates [https://forms.gle/XMKr1nNsJieUK4jD6 upload your slide here] by 2/9 noon |
| − | *2/15 University Holiday: Presidents' Day | + | *2/15 NO CLASS (University Holiday: Presidents' Day) |
*2/17 Language and vision | *2/17 Language and vision | ||
** [https://openreview.net/pdf?id=YicbFdNTTy An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale] | ** [https://openreview.net/pdf?id=YicbFdNTTy An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale] | ||
** [https://openaccess.thecvf.com/content_CVPR_2020/papers/Chaplot_Neural_Topological_SLAM_for_Visual_Navigation_CVPR_2020_paper.pdf Neural Topological SLAM for Visual Navigation] | ** [https://openaccess.thecvf.com/content_CVPR_2020/papers/Chaplot_Neural_Topological_SLAM_for_Visual_Navigation_CVPR_2020_paper.pdf Neural Topological SLAM for Visual Navigation] | ||
| − | *2/22 Deep Reinforcement Learning 1 | + | *2/22 Deep Reinforcement Learning 1 |
| − | + | ** [https://papers.nips.cc/paper/2017/hash/9e82757e9a1c12cb710ad680db11f6f1-Abstract.html Imagination-Augmented Agents for Deep Reinforcement Learning] | |
** [https://openreview.net/pdf?id=S1g2skStPB Causal Discovery with Reinforcement Learning] | ** [https://openreview.net/pdf?id=S1g2skStPB Causal Discovery with Reinforcement Learning] | ||
| + | *2/24 Deep Reinforcement Learning 2 (HW2 due: 02/26 Friday 11:59pm) | ||
| + | ** [https://arxiv.org/abs/1705.05363 Curiosity-driven Exploration by Self-supervised Prediction] | ||
** [https://www.nature.com/articles/s41586-019-1724-z Grandmaster level in StarCraft II using multi-agent reinforcement learning] | ** [https://www.nature.com/articles/s41586-019-1724-z Grandmaster level in StarCraft II using multi-agent reinforcement learning] | ||
** [https://www.nature.com/articles/s41586-020-03051-4 Mastering Atari, Go, chess and shogi by planning with a learned model] | ** [https://www.nature.com/articles/s41586-020-03051-4 Mastering Atari, Go, chess and shogi by planning with a learned model] | ||
| Line 34: | Line 44: | ||
** [https://arxiv.org/abs/1701.07875 Wasserstein GAN] | ** [https://arxiv.org/abs/1701.07875 Wasserstein GAN] | ||
** [https://arxiv.org/abs/1703.10717 Boundary Equilibrium GAN] | ** [https://arxiv.org/abs/1703.10717 Boundary Equilibrium GAN] | ||
| − | *3/3 Project: final presentation (1) | + | * Check out final project presentation schedule here: [https://docs.google.com/spreadsheets/d/1T791ZMd4l6IZrdcWhpTuZx-37f_XWEgfd_BtGmEXRrw/edit?usp=sharing schedule] |
| − | *3/8 Project: final presentation (2) | + | *3/3 Project: final presentation (1) [https://forms.gle/7d2iVhT322bzY9UCA submission link] by 3/2 noon. |
| − | *3/10 Project: final presentation (3) | + | *3/8 Project: final presentation (2) [https://forms.gle/7d2iVhT322bzY9UCA submission link] by 3/7 noon. |
| + | *3/10 Project: final presentation (3) [https://forms.gle/7d2iVhT322bzY9UCA submission link] by 3/9 noon. | ||
*3/19 23:59PM PT Project Final Report Due [https://forms.gle/kgN8n8XDz83NWdxo9 submission link]. | *3/19 23:59PM PT Project Final Report Due [https://forms.gle/kgN8n8XDz83NWdxo9 submission link]. | ||
Latest revision as of 22:56, 21 February 2021
Checkout the class presentation schedule for additional readings: Class Presentation Schedule
- 1/4 Introduction, logistics, and deep learning.
- 1/6 Tips for a successful class project
- 1/11 Neural network basics, & backpropagation
- 1/13 Word embeddings (Project proposal due 23:59PT 1/13 submission link, HW1 out)
- 1/18 NO CLASS (University Holiday: Martin Luther King Jr. Day)
- 1/20 RNNs
- 1/25 LSTMs/GRUs
- 1/27 Sequence-to-sequence models
- 2/1 Convolutional Neural Networks (HW1 due and HW2 out)
- 2/3 Attention mechanisms
- 2/8 Transformer and BERT (Mid-term report due submission link)
- 2/10 Mid-term project updates upload your slide here by 2/9 noon
- 2/15 NO CLASS (University Holiday: Presidents' Day)
- 2/17 Language and vision
- 2/22 Deep Reinforcement Learning 1
- 2/24 Deep Reinforcement Learning 2 (HW2 due: 02/26 Friday 11:59pm)
- 3/1 Generative Adversarial Networks
- Check out final project presentation schedule here: schedule
- 3/3 Project: final presentation (1) submission link by 3/2 noon.
- 3/8 Project: final presentation (2) submission link by 3/7 noon.
- 3/10 Project: final presentation (3) submission link by 3/9 noon.
- 3/19 23:59PM PT Project Final Report Due submission link.
