DL 6890 Deep Learning

Paper Presentations

- Deep Reinforcement Learning:
- presented by Quintin Fettes and Lukas Palmer, Apr 10.
- Human-level control through deep reinforcement learning, Mnih et al., Nature, 2015.
- Noisy Networks for Exploration, Fortunato et al., DeepMind, ICLR 2018.
- Rainbow: Combining Improvements in Deep Reinforcement Learning, Hessel et al., DeepMind, AAAI 2018.
- Silver's Tutorials on Deep Reinforcement Learning

- Combining Sequence Models with Reinforcement Learning:
- presented by Yadi Zhou, Apr 10.
- Sequence Tutor: Conservative Fine-Tuning of Sequence Generation Models with KL-control, Jaques et al., ICML 2017.
- Tuning Recurrent Neural Networks with Reinforcement Learning, Natasha Jaques, Magenta Blog, 2016.

- Image Segmentation and Generation: Upsampling through Transposed Convolution and Max Unpooling:
- presented by Nidal Abuhajar and Weizhen Cai, April 12.
- Visualizing and Understanding Convolutional Networks, Zeiler and Fergus, ECCV 2014.
- Fully Convolutional Networks for Semantic Segmentation, Long et al., CVPR 2015.
- A Guide to Transposed Convolutions, Dumoulin and Visin, CoRR 2018.

- Generative Adversarial Networks (GAN):
- presented by James Engelmann, April 12.
- Generative Adversarial Nets, Goodfellow et al., NIPS 2014.
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks, Radford et al., ICLR 2016.
- Are GANs Created Equal? A Large-Scale Study, Lucic et al., Google Brain 2017.
- Open AI blog on Generative Models

- Deep Networks and Generalization:
- presented by Gareth Whaley, Apr 17.
- Understanding deep learning requires rethinking generalization, Zhang et al., ICLR 2017.
- Musings on Deep Learning: Properties of SGD, Zhang et al., CBMM Memo, MIT 2017.
- Opening the black box of Deep Neural Networks via Information, Schwartz-Ziv and Tishby, ICRI-CI 2017.
- New Theory Cracks Open the Black Box of Deep Learning, Natalie Wolchover, Quanta Magazine, 2017.
- On Generalization and Regularization in Deep Learning, Lemberger, CoRR 2017.

- Adversarial Examples: Part 1 and Part 2:
- presented by Colton Smith and Yiran Liu, Apr 17.
- Adversarial Examples Against Deep Neural Networks, Berkelei AI blog, 2017.
- Intriguing properties of neural networks, Szegedy et al., ICLR 2014.
- Explaining and Harnessing Adversarial Examples, Goodfellow et al., ICLR 2015.
- Robust Adversarial Examples, OpenAI blog, 2017.
- Synthesizing Robust Adversarial Examples, Athalye et al., ICLR 2018.
- DeepFool: a simple and accurate method to fool deep neural networks, Moosavi et al., CVPR 2016
- Towards Evaluating the Robustness of Neural Networks, Carlini and Wagner, IEEE 2017.

- Memory Augmented Networks:
- presented by Oscar Uduehi, Apr 19.
- Hybrid computing using a neural network with dynamic external memory, Graves et al., Nature 2015.
- A Context-aware Attention Network for Interactive Question Answering, Li et a., KDD 2017.
- End-To-End Memory Networks, Sukhbaatar et al., NIPS 2015.
- Memory Networks for Language Understanding, ICML Tutorial 2016.

- Capsule Networks:
- presented by Reza Katebi, Apr 19.
- Dynamic Routing Between Capsules, Sabour et al., NIPS 2017.

- Deep Learning and Newtonian Physics:
- presented by Ohioma Eboreime, Apr 19.
- Visual Interaction Networks: Learning a Physics Simulator from Video, Watters et al., NIPS 2017.
- Newtonian Image Understanding: Unfolding the Dynamics of Objects in Static Images, Mottaghi et al., CVPR 2016.
- Learning physical intuition of block towers by example, Lerer et al., ICML 2016.

- Combining Deep Learning with Conditional Random Fields:
- presented by Kristen Masada, April 24.
- Segmental Recurrent Neural Networks, Kong, Dyer, and Smith, ICLR 2016.

- Semantic Parsing with Sequence-to-Sequence Models:
- presented by Zhongen Li, Apr 24.
- Language to Logical Form with Neural Attention, Dong and Lapata, ACL 2016.