User contributions for Ashishgaurav
A user with 78 edits. Account created on 25 September 2017.
30 November 2017
- 12:1912:19, 30 November 2017 diff hist +85 Deep Alternative Neural Network: Exploring Contexts As Early As Possible For Action Recognition →Introduction current
- 12:1612:16, 30 November 2017 diff hist +29 Deep Alternative Neural Network: Exploring Contexts As Early As Possible For Action Recognition →Deep Alternative Neural Network:
- 12:0412:04, 30 November 2017 diff hist +640 STAT946F17/Conditional Image Generation with PixelCNN Decoders →Critique
- 11:5311:53, 30 November 2017 diff hist +199 STAT946F17/ Automated Curriculum Learning for Neural Networks →Conclusion
- 11:4711:47, 30 November 2017 diff hist +16 STAT946F17/ Automated Curriculum Learning for Neural Networks No edit summary
- 11:3711:37, 30 November 2017 diff hist +193 STAT946F17/Decoding with Value Networks for Neural Machine Translation →Value Network for NMT
- 11:1611:16, 30 November 2017 diff hist +20 STAT946F17/Decoding with Value Networks for Neural Machine Translation →Neural Machine Translation
28 November 2017
- 14:0214:02, 28 November 2017 diff hist +248 Hierarchical Question-Image Co-Attention for Visual Question Answering →Ablation Study
- 12:1212:12, 28 November 2017 diff hist +103 Hierarchical Question-Image Co-Attention for Visual Question Answering No edit summary
- 12:0612:06, 28 November 2017 diff hist +413 Conditional Image Synthesis with Auxiliary Classifier GANs No edit summary
20 November 2017
- 20:2620:26, 20 November 2017 diff hist −48 Deep Exploration via Bootstrapped DQN No edit summary
19 November 2017
- 21:5221:52, 19 November 2017 diff hist +98 Deep Exploration via Bootstrapped DQN No edit summary
- 16:5816:58, 19 November 2017 diff hist +4 Deep Alternative Neural Network: Exploring Contexts As Early As Possible For Action Recognition →Alternative Layer
- 16:5616:56, 19 November 2017 diff hist +2 Deep Exploration via Bootstrapped DQN →Double Deep Q Learning
- 16:5616:56, 19 November 2017 diff hist +35 Deep Exploration via Bootstrapped DQN →How does Double Q Learning work? [[#References|[9]]]
- 04:4304:43, 19 November 2017 diff hist +4,496 Deep Exploration via Bootstrapped DQN No edit summary
- 04:1704:17, 19 November 2017 diff hist +10 N File:cumulative rewards bdqn.png this paper current
- 04:0304:03, 19 November 2017 diff hist +10 N File:bdqn improvement.png this paper current
- 03:5703:57, 19 November 2017 diff hist +10 N File:atari results bootstrapped dqn.png this paper current
- 03:3503:35, 19 November 2017 diff hist +10 N File:scale k p.png this paper current
- 03:2403:24, 19 November 2017 diff hist +1,978 Deep Exploration via Bootstrapped DQN No edit summary
- 03:0103:01, 19 November 2017 diff hist +10 N File:deep exploration results.png this paper current
- 02:5402:54, 19 November 2017 diff hist +10 N File:deep exploration example.png from paper current
- 02:3202:32, 19 November 2017 diff hist +1,589 Deep Exploration via Bootstrapped DQN No edit summary
- 01:5601:56, 19 November 2017 diff hist +2,672 Deep Exploration via Bootstrapped DQN No edit summary
- 00:2900:29, 19 November 2017 diff hist +2,293 Deep Exploration via Bootstrapped DQN No edit summary
18 November 2017
- 22:0022:00, 18 November 2017 diff hist +15 Deep Exploration via Bootstrapped DQN →Deep Q Learning [[#References|[5]]]
- 21:5621:56, 18 November 2017 diff hist +6,372 Deep Exploration via Bootstrapped DQN No edit summary
- 19:4719:47, 18 November 2017 diff hist +108 N File:DQN arch.png https://leonardoaraujosantos.gitbooks.io/artificial-inteligence/content/image_folder_7/DQNBreakoutBlocks.png current
17 November 2017
- 17:5917:59, 17 November 2017 diff hist +34 Deep Exploration via Bootstrapped DQN →Status: In Progress
16 November 2017
- 11:4611:46, 16 November 2017 diff hist −4 LightRNN: Memory and Computation-Efficient Recurrent Neural Networks →Remarks
- 11:4611:46, 16 November 2017 diff hist +4 LightRNN: Memory and Computation-Efficient Recurrent Neural Networks →LightRNN Structure
- 11:4611:46, 16 November 2017 diff hist +3 LightRNN: Memory and Computation-Efficient Recurrent Neural Networks →Motivations
- 11:3911:39, 16 November 2017 diff hist +171 "Why Should I Trust You?": Explaining the Predictions of Any Classifier →References
- 11:3711:37, 16 November 2017 diff hist +4 "Why Should I Trust You?": Explaining the Predictions of Any Classifier →Remarks and Critique
- 11:2611:26, 16 November 2017 diff hist 0 "Why Should I Trust You?": Explaining the Predictions of Any Classifier →Desired Characteristics for Explanations
- 10:3010:30, 16 November 2017 diff hist +445 STAT946F17/ Teaching Machines to Describe Images via Natural Language Feedback No edit summary
- 10:1710:17, 16 November 2017 diff hist +12 STAT946F17/ Teaching Machines to Describe Images via Natural Language Feedback →Crowd-sourcing Human Feedback
- 10:1410:14, 16 November 2017 diff hist +168 STAT946F17/ Teaching Machines to Describe Images via Natural Language Feedback →References
- 10:1410:14, 16 November 2017 diff hist +158 STAT946F17/ Teaching Machines to Describe Images via Natural Language Feedback →Related Works
- 00:0400:04, 16 November 2017 diff hist +1,444 Deep Exploration via Bootstrapped DQN No edit summary
15 November 2017
- 23:2123:21, 15 November 2017 diff hist +76 N File:dropout results.png From https://papers.nips.cc/paper/6501-deep-exploration-via-bootstrapped-dqn current
- 21:4821:48, 15 November 2017 diff hist +1,652 Deep Exploration via Bootstrapped DQN No edit summary
- 19:2619:26, 15 November 2017 diff hist +3,336 Deep Exploration via Bootstrapped DQN →Gist
- 13:3613:36, 15 November 2017 diff hist +64 N File:thompson sampling coin example.png https://www.quora.com/What-is-Thompson-sampling-in-laymans-terms current
- 12:3812:38, 15 November 2017 diff hist +66 N File:multiarmedbandit.jpg https://blogs.mathworks.com/images/loren/2016/multiarmedbandit.jpg current
14 November 2017
- 11:3811:38, 14 November 2017 diff hist +1 Imagination-Augmented Agents for Deep Reinforcement Learning →Experiment
- 11:3711:37, 14 November 2017 diff hist +918 Imagination-Augmented Agents for Deep Reinforcement Learning No edit summary
- 10:5710:57, 14 November 2017 diff hist −4 Dialog-based Language Learning →Training strategies
- 10:4410:44, 14 November 2017 diff hist +20 Dialog-based Language Learning →Dialog-based Supervision tasks