User contributions for Jmmoosa
Jump to navigation
Jump to search
17 December 2018
- 13:3813:38, 17 December 2018 diff hist +1 learn what not to learn →Related Work current
- 13:2813:28, 17 December 2018 diff hist 0 DON'T DECAY THE LEARNING RATE , INCREASE THE BATCH SIZE →TRAINING IMAGENET IN 30 MINUTES current
29 November 2018
- 13:3213:32, 29 November 2018 diff hist +42 CapsuleNets No edit summary
- 12:4612:46, 29 November 2018 diff hist 0 ShakeDrop Regularization →Existing Methods
- 12:4412:44, 29 November 2018 diff hist +4 stat946F18/Autoregressive Convolutional Neural Networks for Asynchronous Time Series →Experiments
- 12:3712:37, 29 November 2018 diff hist 0 stat946F18/Autoregressive Convolutional Neural Networks for Asynchronous Time Series →Results
- 12:3612:36, 29 November 2018 diff hist 0 stat946F18/Autoregressive Convolutional Neural Networks for Asynchronous Time Series →Training details
27 November 2018
- 13:4113:41, 27 November 2018 diff hist +225 policy optimization with demonstrations →Discussion on Existing LfD Methods
- 13:3713:37, 27 November 2018 diff hist +17 policy optimization with demonstrations →Policy Optimization with Demonstration (POfD)
- 13:3313:33, 27 November 2018 diff hist +202 policy optimization with demonstrations →Policy Optimization with Demonstration (POfD)
- 13:2713:27, 27 November 2018 diff hist +83 Visual Reinforcement Learning with Imagined Goals →Experiments
- 13:1713:17, 27 November 2018 diff hist 0 Visual Reinforcement Learning with Imagined Goals →Conclusion & Future Work
- 12:5412:54, 27 November 2018 diff hist +1 Unsupervised Neural Machine Translation →Methodology
- 12:4112:41, 27 November 2018 diff hist +2 Visual Reinforcement Learning with Imagined Goals →Related Work
- 12:2712:27, 27 November 2018 diff hist +4 Unsupervised Neural Machine Translation →Experiments and Results
23 November 2018
- 11:2311:23, 23 November 2018 diff hist +41 Unsupervised Neural Machine Translation →Critique
- 11:1611:16, 23 November 2018 diff hist +45 Deep Reinforcement Learning in Continuous Action Spaces a Case Study in the Game of Simulated Curling →Policy Network
- 11:1411:14, 23 November 2018 diff hist 0 N File:policy-value-net.PNG No edit summary current
- 11:0211:02, 23 November 2018 diff hist +322 Deep Reinforcement Learning in Continuous Action Spaces a Case Study in the Game of Simulated Curling →Monte Carlo Tree Search
- 10:4810:48, 23 November 2018 diff hist +31 a neural representation of sketch drawings →Unconditional Generation