Wednesday, December 20
Session I "Theory and Core Algorithms"
09:10am-09:40am On the Power of Randomly Initialized Gradient Descent for Learning Convolutional Neural Networks (by Shaolei Du)
09:40am-10:10am Opening the black of deep neural networks via information (by Ravid Schwartz-Ziv)
10:10am-10:30am Tea break
10:30am-11:00am Nonconvex Sparse Blind Deconvolution: Global Geometry and Efficient Methods (by Yuqian Zhang)
11:00am-11:30am Adversarial regularized autoencoders and error encoding network (by Junbo Zhao)
11:30am-12:00pm Enhancing Iterative Algorithms using Neural Networks (by David Wipf) (Keynote)
Session II "Application: Game and Generalizable Intelligence"
01:15pm-01:45pm Sample-Efficient Deep RL for Robotics: Generalizing On-policy, Off-policy, and Model-based Approaches (by Shixiang Gu)
01:45pm-02:15pm Towards a wholistic approach to dexterous and cluttered manipulation (by Jiaji Zhou)
02:15pm-02:45pm Towards Generalizable Robot Learning with Perception (by Yuke Zhu)
02:45pm-03:15pm Effective Master-Slave Communication for Multi-Agent Deep Reinforcement Learning (by Xiangyu Kong)
03:15pm-03:45pm AI in Games: Achievements and Challenges (by Yuandong Tian) (Keynote)
04:00pm-04:15pm Tea break
Session III "Application: Natural Language Processing and Computer Vision"
04:15pm-04:35pm Present and Future of Natural Language Processing - With Dialogue as Example (by Hang Li) (Keynote)
04:35pm-05:05pm Think out of black-box (by Zhengdong Lu)
05:05pm-05:35pm Learning to Reason with End-to-End Neural Module Networks (by Ronghang Hu)
05:35pm-06:05pm On unifying deep generative models (by Zhiting Hu)
06:05pm-06:35pm Deep Multitask Learning for Semantic Dependency Parsing (by Hao Peng)
Thursday, December 21
Session IV "System"
09:00am-09:30am TVM: An End to End IR Stack for Deep Learning Systems (by Tianqi Chen)
09:30am-10:00am Tofu: Distributing Tensor Computation Automatically for Deep Learning Systems (by Minjie Wang)
10:15am-10:30am Tea break
Session V "Creativity and Music with AI"
10:30am-11:00am Empowering music intelligent systems with expression and interactivity (by Gus Xia)
11:00am-11:30pm Creativity in Musical Intelligence (by Zhengshan Shi)
11:30am-12:00pm Crowd Sourcing Clothes Design Directed by Adversarial Neural Networks (by Hiroyuki Osone & Daitetsu Sato)