Seminars@UTS

Tentative Seminars:

Time: 11:00AM AEST, Every Sunday

Location: Metting Room@CAI in Building 11 UTS

No	Date	Title/Topic	Speaker
1	20 Aug 2017	Implimentation of basic RL algorithms: Dynamic programming, Monte Carlo, Temporal Difference and DQN	Peike Li
2	20 Aug 2017	Stochastic Variance Reduction Methdos for Policy Evaluation [Slides]	Yan Yan
3	27 Aug 2017	Recurrent Models of Visual Attention	Hehe Fan
4	27 Aug 2017	A Light Touch on Introduction to Reinforcement Learning	Linchao Zhu
5	3 Sept 2017	Action-Decision Networks for Visual Tracking with Deep Reinforcement Learning [Project page, Github, Slides]	Xuanyi Dong
6	3 Sept 2017	FeUdal Networks for Hierarchical Reinforcement Learning [Github, Slides ]	Guoliang Kang
7	10 Sept 2017	Train faster, generalize better: Stability of stochastic gradient descent [Arxiv]	Hu Zhang
8	10 Sept 2017	Implementation of policy-based RL algorithms	Peike Li
9	17 Sept 2017	Learning Cooperative Visual Dialog Agents with Deep Reinforcement Learning [Slides, Dialog Demo]	Hehe Fan
10	17 Sept 2017	Neural Optimizer Search with Reinforcement Learning [Slides ]	Yan Yan
11	24 Sept 2017	Imagination-Augmented Agents for Deep Reinforcement Learning [ Slides ]	Zhun Zhong
12	24 Sept 2017	The Shattered Gradients Problem: If resnets are the answer, then what is the question? [ Slides ]	Guoliang Kang
13	1 Oct 2017	Trust Region Policy Optimization	Peike Li
14	1 Oct 2017	Self-critical Sequence Training for Image Captioning [Slides]	Jiaxu Miao
15	8 Oct 2017	Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding + Opening the Black Box of Deep Neural Networks via Information [Slides]	Yang He
16	8 Oct 2017	Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks [Github, Project Page]	Zhedong Zheng
17	22 Oct 2017	Video Propagation Networks [Slides, A review on DAVIS challenge]	Guang Li