Difference between revisions of "Winter 2018 CS291A Syllabus"
From courses
(update student choices) |
|||
| Line 11: | Line 11: | ||
**Vivek : [http://jmlr.org/papers/volume15/srivastava14a/srivastava14a.pdf Dropout: A simple way to prevent neural networks from overfitting (2014), N. Srivastava et al., JMLR 2014] | **Vivek : [http://jmlr.org/papers/volume15/srivastava14a/srivastava14a.pdf Dropout: A simple way to prevent neural networks from overfitting (2014), N. Srivastava et al., JMLR 2014] | ||
*02/01 Recursive Neural Networks | *02/01 Recursive Neural Networks | ||
| − | ** : [http://www.robotics.stanford.edu/~ang/papers/emnlp12-SemanticCompositionalityRecursiveMatrixVectorSpaces.pdf Semantic Compositionality through Recursive Matrix-Vector Spaces, Socher et al., EMNLP 2012] | + | **April : [http://www.robotics.stanford.edu/~ang/papers/emnlp12-SemanticCompositionalityRecursiveMatrixVectorSpaces.pdf Semantic Compositionality through Recursive Matrix-Vector Spaces, Socher et al., EMNLP 2012] |
** : [https://nlp.stanford.edu/pubs/SocherBauerManningNg_ACL2013.pdf Parsing with Compositional Vector Grammars, Socher et al., ACL 2013] | ** : [https://nlp.stanford.edu/pubs/SocherBauerManningNg_ACL2013.pdf Parsing with Compositional Vector Grammars, Socher et al., ACL 2013] | ||
** : [https://nlp.stanford.edu/~socherr/EMNLP2013_RNTN.pdf Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank, Socher et al., EMNLP 2013] | ** : [https://nlp.stanford.edu/~socherr/EMNLP2013_RNTN.pdf Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank, Socher et al., EMNLP 2013] | ||
| Line 17: | Line 17: | ||
**Lukas : [https://pdfs.semanticscholar.org/8adb/8257a423f55b1f20ba62c8b20118d76a25c7.pdf A Learning Algorithm for Continually Running Fully Recurrent Neural Networks, Ronald J. Williams and David Zipser, 1989] | **Lukas : [https://pdfs.semanticscholar.org/8adb/8257a423f55b1f20ba62c8b20118d76a25c7.pdf A Learning Algorithm for Continually Running Fully Recurrent Neural Networks, Ronald J. Williams and David Zipser, 1989] | ||
**Yifu : [http://www.fit.vutbr.cz/research/groups/speech/publi/2010/mikolov_interspeech2010_IS100722.pdf Recurrent neural network based language model] | **Yifu : [http://www.fit.vutbr.cz/research/groups/speech/publi/2010/mikolov_interspeech2010_IS100722.pdf Recurrent neural network based language model] | ||
| − | ** : [https://arxiv.org/pdf/1308.0850.pdf Generating Sequences With Recurrent Neural Networks, Alex Graves, 2013 arxiv] | + | **John : [https://arxiv.org/pdf/1308.0850.pdf Generating Sequences With Recurrent Neural Networks, Alex Graves, 2013 arxiv] |
*02/08 LSTMs/GRUs | *02/08 LSTMs/GRUs | ||
**Liu : [http://www.bioinf.jku.at/publications/older/2604.pdf Long short term memory, S. Hochreiter and J. Schmidhuber, Neural Computation, 1997] | **Liu : [http://www.bioinf.jku.at/publications/older/2604.pdf Long short term memory, S. Hochreiter and J. Schmidhuber, Neural Computation, 1997] | ||
| − | ** : [https://arxiv.org/pdf/1409.1259.pdf On the Properties of Neural Machine Translation: Encoder–Decoder Approaches, Cho et al., 2014] | + | **Zhiyu : [https://arxiv.org/pdf/1409.1259.pdf On the Properties of Neural Machine Translation: Encoder–Decoder Approaches, Cho et al., 2014] |
** : [https://arxiv.org/pdf/1502.02367v3.pdf Gated Feedback Recurrent Neural Networks, Chung et al., ICML 2015] | ** : [https://arxiv.org/pdf/1502.02367v3.pdf Gated Feedback Recurrent Neural Networks, Chung et al., ICML 2015] | ||
*02/13 Sequence-to-sequence models and neural machine translation (HW1 due and HW2 out) | *02/13 Sequence-to-sequence models and neural machine translation (HW1 due and HW2 out) | ||
| − | ** : [https://arxiv.org/pdf/1406.1078.pdf Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation, Cho et al., EMNLP 2014] | + | **Ryan : [https://arxiv.org/pdf/1406.1078.pdf Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation, Cho et al., EMNLP 2014] |
**Yanju : [https://papers.nips.cc/paper/5346-sequence-to-sequence-learning-with-neural-networks.pdf Sequence to Sequence Learning with Neural Networks, Sutskever et al., NIPS 2014] | **Yanju : [https://papers.nips.cc/paper/5346-sequence-to-sequence-learning-with-neural-networks.pdf Sequence to Sequence Learning with Neural Networks, Sutskever et al., NIPS 2014] | ||
** : [http://www.aclweb.org/anthology/P16-1100 Achieving Open Vocabulary Neural Machine Translation with Hybrid Word-Character Models, Luong and Manning, ACL 2016] | ** : [http://www.aclweb.org/anthology/P16-1100 Achieving Open Vocabulary Neural Machine Translation with Hybrid Word-Character Models, Luong and Manning, ACL 2016] | ||
*02/15 Attention mechanisms | *02/15 Attention mechanisms | ||
**Jing : [https://arxiv.org/pdf/1409.0473.pdf NEURAL MACHINE TRANSLATION BY JOINTLY LEARNING TO ALIGN AND TRANSLATE, Bahdanau et al., ICLR 2015] | **Jing : [https://arxiv.org/pdf/1409.0473.pdf NEURAL MACHINE TRANSLATION BY JOINTLY LEARNING TO ALIGN AND TRANSLATE, Bahdanau et al., ICLR 2015] | ||
| − | ** : [https://arxiv.org/abs/1506.03340 Teaching Machines to Read and Comprehend, NIPS 2015] | + | **Abhay : [https://arxiv.org/abs/1506.03340 Teaching Machines to Read and Comprehend, NIPS 2015] |
| − | ** : [http://papers.nips.cc/paper/5846-end-to-end-memory-networks.pdf End-to-end memory networks, NIPS 2015] | + | **Ashwini : [http://papers.nips.cc/paper/5846-end-to-end-memory-networks.pdf End-to-end memory networks, NIPS 2015] |
*02/20 Convolutional Neural Networks (Mid-term report due to Grader: Ke Ni <ke00@ucsb.edu>) | *02/20 Convolutional Neural Networks (Mid-term report due to Grader: Ke Ni <ke00@ucsb.edu>) | ||
| − | ** : [http://ronan.collobert.com/pub/matos/2011_nlp_jmlr.pdf Natural Language Processing (Almost) from Scratch, Collobert et al., JMLR 2011] | + | **Esther : [http://ronan.collobert.com/pub/matos/2011_nlp_jmlr.pdf Natural Language Processing (Almost) from Scratch, Collobert et al., JMLR 2011] |
| − | ** : [https://arxiv.org/pdf/1510.03820.pdf A Sensitivity Analysis of (and Practitioners’ Guide to) Convolutional Neural Networks for Sentence Classification, Zhang and Wallace, Arxiv 2015] | + | **Shabnam : [https://arxiv.org/pdf/1510.03820.pdf A Sensitivity Analysis of (and Practitioners’ Guide to) Convolutional Neural Networks for Sentence Classification, Zhang and Wallace, Arxiv 2015] |
**Jiawei : [http://papers.nips.cc/paper/5550-convolutional-neural-network-architectures-for-matching-natural-language-sentences Convolutional Neural Network Architectures for Matching Natural Language Sentences, Hu et al., NIPS 2014] | **Jiawei : [http://papers.nips.cc/paper/5550-convolutional-neural-network-architectures-for-matching-natural-language-sentences Convolutional Neural Network Architectures for Matching Natural Language Sentences, Hu et al., NIPS 2014] | ||
*02/22 Language and vision | *02/22 Language and vision | ||
| Line 39: | Line 39: | ||
**Richika : [http://www.cv-foundation.org/openaccess/content_iccv_2015/papers/Zhu_Aligning_Books_and_ICCV_2015_paper.pdf Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books, Zhu et al., ICCV 2015] | **Richika : [http://www.cv-foundation.org/openaccess/content_iccv_2015/papers/Zhu_Aligning_Books_and_ICCV_2015_paper.pdf Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books, Zhu et al., ICCV 2015] | ||
*02/27 Deep Reinforcement Learning 1 (HW2 due) | *02/27 Deep Reinforcement Learning 1 (HW2 due) | ||
| − | ** : [https://aclweb.org/anthology/D16-1127, Deep Reinforcement Learning for Dialogue Generation, Li et al., EMNLP 2016] | + | **Karthik : [https://aclweb.org/anthology/D16-1127, Deep Reinforcement Learning for Dialogue Generation, Li et al., EMNLP 2016] |
**David : [https://arxiv.org/abs/1603.07954 Improving Information Extraction by Acquiring External Evidence with Reinforcement Learning, Narasimh et al., EMNLP 2016] | **David : [https://arxiv.org/abs/1603.07954 Improving Information Extraction by Acquiring External Evidence with Reinforcement Learning, Narasimh et al., EMNLP 2016] | ||
| − | ** : [http://www.aclweb.org/anthology/P16-1153 Deep Reinforcement Learning with a Natural Language Action Space, He et al., ACL 2016] | + | **Michael : [http://www.aclweb.org/anthology/P16-1153 Deep Reinforcement Learning with a Natural Language Action Space, He et al., ACL 2016] |
*03/01 Deep Reinforcement Learning 2 | *03/01 Deep Reinforcement Learning 2 | ||
**Trevor : [https://www.cs.toronto.edu/~vmnih/docs/dqn.pdf Playing Atari with Deep Reinforcement Learning, Mnih et al., NIPS workshop 2013] | **Trevor : [https://www.cs.toronto.edu/~vmnih/docs/dqn.pdf Playing Atari with Deep Reinforcement Learning, Mnih et al., NIPS workshop 2013] | ||
Revision as of 20:19, 18 January 2018
- 01/16 Introduction, logistics, NLP, and deep learning.
- 01/18 Tips for a successful class project
- 01/23 NLP Tasks
- 01/25 Word embeddings
- : Efficient Non-parametric Estimation of Multiple Embeddings per Word in Vector Space, Neelakantan et al., EMNLP 2014
- Arya: Glove: Global Vectors for Word Representation, J Pennington, R Socher, CD Manning - EMNLP, 2014
- : AutoExtend: Extending Word Embeddings to Embeddings for Synsets and Lexemes, Rothe and Schutze, ACL 2015
- 01/30 Neural network basics (Project proposal due to Grader: Ke Ni < ke00@ucsb.edu> , HW1 out)
- 02/01 Recursive Neural Networks
- 02/06 RNNs
- 02/08 LSTMs/GRUs
- 02/13 Sequence-to-sequence models and neural machine translation (HW1 due and HW2 out)
- Ryan : Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation, Cho et al., EMNLP 2014
- Yanju : Sequence to Sequence Learning with Neural Networks, Sutskever et al., NIPS 2014
- : Achieving Open Vocabulary Neural Machine Translation with Hybrid Word-Character Models, Luong and Manning, ACL 2016
- 02/15 Attention mechanisms
- 02/20 Convolutional Neural Networks (Mid-term report due to Grader: Ke Ni <ke00@ucsb.edu>)
- Esther : Natural Language Processing (Almost) from Scratch, Collobert et al., JMLR 2011
- Shabnam : A Sensitivity Analysis of (and Practitioners’ Guide to) Convolutional Neural Networks for Sentence Classification, Zhang and Wallace, Arxiv 2015
- Jiawei : Convolutional Neural Network Architectures for Matching Natural Language Sentences, Hu et al., NIPS 2014
- 02/22 Language and vision
- Sai : Show and Tell: A Neural Image Caption Generator, CVPR 2015
- Xiyou : Deep Visual-Semantic Alignments for Generating Image Descriptions, Andrej Karpathy and Li Fei-Fei, CVPR 2015
- Richika : Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books, Zhu et al., ICCV 2015
- 02/27 Deep Reinforcement Learning 1 (HW2 due)
- Karthik : Deep Reinforcement Learning for Dialogue Generation, Li et al., EMNLP 2016
- David : Improving Information Extraction by Acquiring External Evidence with Reinforcement Learning, Narasimh et al., EMNLP 2016
- Michael : Deep Reinforcement Learning with a Natural Language Action Space, He et al., ACL 2016
- 03/01 Deep Reinforcement Learning 2
- 03/06 Unsupervised Learning
- 03/08 Project: final presentation (1)
- 03/13 Project: final presentation (2)
- 03/15 Project: final presentation (3)
- 03/23 23:59PM PT Project Final Report Due. Grader: Ke Ni <ke00@ucsb.edu>
