User contributions for X832zhan
Jump to navigation
Jump to search
29 November 2018
- 13:2913:29, 29 November 2018 diff hist +250 DETECTING STATISTICAL INTERACTIONS FROM NEURAL NETWORK WEIGHTS →Conclusion
- 13:1013:10, 29 November 2018 diff hist +173 DETECTING STATISTICAL INTERACTIONS FROM NEURAL NETWORK WEIGHTS →Interaction
- 12:5112:51, 29 November 2018 diff hist +13 DETECTING STATISTICAL INTERACTIONS FROM NEURAL NETWORK WEIGHTS →Related Work
- 12:5012:50, 29 November 2018 diff hist +141 DETECTING STATISTICAL INTERACTIONS FROM NEURAL NETWORK WEIGHTS →Related Work
- 12:4512:45, 29 November 2018 diff hist +353 DETECTING STATISTICAL INTERACTIONS FROM NEURAL NETWORK WEIGHTS →Introduction
- 02:1902:19, 29 November 2018 diff hist +139 learn what not to learn →Conclusion
- 02:1402:14, 29 November 2018 diff hist +464 learn what not to learn →Action Elimination
- 02:0102:01, 29 November 2018 diff hist +259 learn what not to learn →Introduction
- 01:0001:00, 29 November 2018 diff hist +116 DON'T DECAY THE LEARNING RATE , INCREASE THE BATCH SIZE →THE EFFECTIVE LEARNING RATE AND THE ACCUMULATION VARIABLE
- 00:5400:54, 29 November 2018 diff hist +227 DON'T DECAY THE LEARNING RATE , INCREASE THE BATCH SIZE →SIMULATED ANNEALING AND THE GENERALIZATION GAP
- 00:3800:38, 29 November 2018 diff hist +388 DON'T DECAY THE LEARNING RATE , INCREASE THE BATCH SIZE →STOCHASTIC GRADIENT DESCENT AND CONVEX OPTIMIZATION
- 00:2000:20, 29 November 2018 diff hist +124 Fix your classifier: the marginal value of training the last weight layer →Possible Caveats
28 November 2018
- 22:3722:37, 28 November 2018 diff hist 0 File:caloss.png X832zhan uploaded a new version of File:caloss.png current
- 22:3722:37, 28 November 2018 diff hist 0 N File:caloss.png No edit summary
- 22:3722:37, 28 November 2018 diff hist +278 Fix your classifier: the marginal value of training the last weight layer →Choosing the projection matrix
- 22:3022:30, 28 November 2018 diff hist +143 Fix your classifier: the marginal value of training the last weight layer →Choosing the projection matrix
- 22:2022:20, 28 November 2018 diff hist +232 ShakeDrop Regularization →Experiments
- 22:1222:12, 28 November 2018 diff hist +169 ShakeDrop Regularization →Proposed Method
- 21:5821:58, 28 November 2018 diff hist +261 ShakeDrop Regularization →Introduction
23 November 2018
- 02:0402:04, 23 November 2018 diff hist +288 stat946F18/Autoregressive Convolutional Neural Networks for Asynchronous Time Series →Gating and weighting mechanisms
- 01:5501:55, 23 November 2018 diff hist +611 stat946F18/Autoregressive Convolutional Neural Networks for Asynchronous Time Series →Time series forecasting
- 01:4001:40, 23 November 2018 diff hist +263 stat946F18/Autoregressive Convolutional Neural Networks for Asynchronous Time Series →Network Training
22 November 2018
- 17:1517:15, 22 November 2018 diff hist +442 Unsupervised Neural Machine Translation →Supervised
- 17:0717:07, 22 November 2018 diff hist +399 Unsupervised Neural Machine Translation →Qualitative Analysis
- 15:4315:43, 22 November 2018 diff hist +67 Deep Reinforcement Learning in Continuous Action Spaces a Case Study in the Game of Simulated Curling →Testing and Results
- 15:3515:35, 22 November 2018 diff hist +834 Deep Reinforcement Learning in Continuous Action Spaces a Case Study in the Game of Simulated Curling →Policy and Value Functions
- 15:0815:08, 22 November 2018 diff hist +135 a neural representation of sketch drawings →Predicting Different Endings of Incomplete Sketches
- 15:0415:04, 22 November 2018 diff hist +100 a neural representation of sketch drawings →Training
- 15:0115:01, 22 November 2018 diff hist +242 a neural representation of sketch drawings →Unconditional Generation
- 14:5314:53, 22 November 2018 diff hist +117 a neural representation of sketch drawings →Dataset
- 03:4803:48, 22 November 2018 diff hist +1 Learning to Navigate in Cities Without a Map →Results
- 03:4703:47, 22 November 2018 diff hist 0 N File:fff8.png No edit summary current
- 03:4603:46, 22 November 2018 diff hist +294 Learning to Navigate in Cities Without a Map →Results
- 03:3503:35, 22 November 2018 diff hist +268 Learning to Navigate in Cities Without a Map →Architectures
- 03:0303:03, 22 November 2018 diff hist +917 conditional neural process →Conditional Neural Process
- 02:3402:34, 22 November 2018 diff hist +188 Mapping Images to Scene Graphs with Permutation-Invariant Structured Prediction →Proof Sketch for Theorem 1
- 02:2502:25, 22 November 2018 diff hist +183 Mapping Images to Scene Graphs with Permutation-Invariant Structured Prediction →Structured prediction
20 November 2018
- 22:2322:23, 20 November 2018 diff hist −5 stat946F18 →Record your contributions here [https://docs.google.com/spreadsheets/d/1SxkjNfhOg_eXWpUnVHuIP93E6tEiXEdpm68dQGencgE/edit?usp=sharing]
- 22:2122:21, 20 November 2018 diff hist +37 policy optimization with demonstrations →Results
- 22:1822:18, 20 November 2018 diff hist +1 policy optimization with demonstrations →Optimization
- 22:1622:16, 20 November 2018 diff hist +1 policy optimization with demonstrations →Optimization
- 22:1622:16, 20 November 2018 diff hist +18 policy optimization with demonstrations →Optimization
- 22:1222:12, 20 November 2018 diff hist −4 policy optimization with demonstrations →Benefits of Exploration with Demonstrations
- 22:0422:04, 20 November 2018 diff hist −1 policy optimization with demonstrations →Preliminaries
- 22:0322:03, 20 November 2018 diff hist +1 policy optimization with demonstrations →Preliminaries
- 21:5321:53, 20 November 2018 diff hist 0 policy optimization with demonstrations →Related Work
- 21:4721:47, 20 November 2018 diff hist +15 policy optimization with demonstrations →Policy Optimization with Demonstration (POfD)
- 21:4421:44, 20 November 2018 diff hist +4,076 policy optimization with demonstrations No edit summary
- 21:1421:14, 20 November 2018 diff hist −5 policy optimization with demonstrations →Critique
- 21:1321:13, 20 November 2018 diff hist +25 policy optimization with demonstrations →Conclusion
- 21:1221:12, 20 November 2018 diff hist +1 policy optimization with demonstrations →Related Work
- 21:1021:10, 20 November 2018 diff hist +12 policy optimization with demonstrations →Intuition
- 21:0921:09, 20 November 2018 diff hist −10 policy optimization with demonstrations →Introduction
- 20:4020:40, 20 November 2018 diff hist 0 policy optimization with demonstrations →Results
- 20:4020:40, 20 November 2018 diff hist 0 policy optimization with demonstrations →Settings
- 20:3920:39, 20 November 2018 diff hist −27 policy optimization with demonstrations →DDPGfD
- 20:3920:39, 20 November 2018 diff hist +5 policy optimization with demonstrations →Discussion on Existing LfD Methods
- 20:3820:38, 20 November 2018 diff hist +1,279 policy optimization with demonstrations No edit summary
- 19:5319:53, 20 November 2018 diff hist 0 N File:pofdf3.png No edit summary current
- 19:5219:52, 20 November 2018 diff hist 0 N File:pofdf2.png No edit summary current
- 19:5219:52, 20 November 2018 diff hist 0 N File:pofdt1.png No edit summary current
- 19:2419:24, 20 November 2018 diff hist 0 N File:pofd.png No edit summary current
- 19:2419:24, 20 November 2018 diff hist 0 N File:eqnlm.png No edit summary current
- 19:2319:23, 20 November 2018 diff hist 0 N File:them2.png No edit summary current
- 19:2319:23, 20 November 2018 diff hist 0 N File:them1.png No edit summary current
- 19:2219:22, 20 November 2018 diff hist 0 N File:ff1.png No edit summary current
- 19:2219:22, 20 November 2018 diff hist 0 N File:asp1.png No edit summary current
- 19:2119:21, 20 November 2018 diff hist 0 N File:lemma1.png No edit summary current
- 19:2119:21, 20 November 2018 diff hist 0 N File:equ2.png No edit summary current
- 19:2019:20, 20 November 2018 diff hist 0 File:def1.png X832zhan uploaded a new version of File:def1.png current
- 19:1919:19, 20 November 2018 diff hist 0 N File:def1.png No edit summary
- 19:1719:17, 20 November 2018 diff hist +15,110 N policy optimization with demonstrations Created page with "= Introduction = ==Introduction== The reinforcement learning (RL) method has made significant progress in a variety of applications, but the exploration problems that how to..."
- 15:5015:50, 20 November 2018 diff hist +114 stat946F18 →Record your contributions here [https://docs.google.com/spreadsheets/d/1SxkjNfhOg_eXWpUnVHuIP93E6tEiXEdpm68dQGencgE/edit?usp=sharing]
18 November 2018
- 23:5023:50, 18 November 2018 diff hist −25 stat946F18 →Record your contributions here [https://docs.google.com/spreadsheets/d/1SxkjNfhOg_eXWpUnVHuIP93E6tEiXEdpm68dQGencgE/edit?usp=sharing]
15 November 2018
- 02:0902:09, 15 November 2018 diff hist 0 N File:figure2.png No edit summary current
- 02:0802:08, 15 November 2018 diff hist +2 Attend and Predict: Understanding Gene Regulation by Selective Attention on Chromatin →Visualization of Attention Weight of bins for each HM of a specific cell type GM12878
- 02:0702:07, 15 November 2018 diff hist +29 m Attend and Predict: Understanding Gene Regulation by Selective Attention on Chromatin →Visualization of Attention Weight of bins for each HM of a specific cell type GM12878
- 02:0002:00, 15 November 2018 diff hist +376 MULTI-VIEW DATA GENERATION WITHOUT VIEW SUPERVISION →Critique
- 01:3501:35, 15 November 2018 diff hist 0 N File:table6.png No edit summary current
- 01:3501:35, 15 November 2018 diff hist 0 N File:table5.png No edit summary current
- 01:3401:34, 15 November 2018 diff hist 0 N File:table4.png No edit summary current
- 01:3401:34, 15 November 2018 diff hist 0 Reinforcement Learning of Theorem Proving →Experimental Results
- 01:3201:32, 15 November 2018 diff hist 0 N File:table3.png No edit summary current
- 01:3101:31, 15 November 2018 diff hist 0 Reinforcement Learning of Theorem Proving →Experimental Results
- 01:2901:29, 15 November 2018 diff hist +933 Reinforcement Learning of Theorem Proving →Experimental Results
13 November 2018
- 01:4301:43, 13 November 2018 diff hist +27 m Predicting Floor Level For 911 Calls with Neural Network and Smartphone Sensor Data No edit summary
- 01:2001:20, 13 November 2018 diff hist +601 Searching For Efficient Multi Scale Architectures For Dense Image Prediction →Result
- 00:5700:57, 13 November 2018 diff hist +191 Searching For Efficient Multi Scale Architectures For Dense Image Prediction →Future work
- 00:3800:38, 13 November 2018 diff hist +4 Zero-Shot Visual Imitation →Related Work
- 00:3800:38, 13 November 2018 diff hist +739 Zero-Shot Visual Imitation →Related Work
- 00:2200:22, 13 November 2018 diff hist +242 Zero-Shot Visual Imitation →Critique
7 November 2018
- 21:2221:22, 7 November 2018 diff hist 0 N File:Co-Teaching Table 8.png No edit summary current
- 21:2221:22, 7 November 2018 diff hist 0 N File:Co-Teaching Table 7.png No edit summary current
- 21:2221:22, 7 November 2018 diff hist +526 Co-Teaching →Results and Discussion
- 18:2318:23, 7 November 2018 diff hist +117 Co-Teaching →Related Works
- 18:1718:17, 7 November 2018 diff hist +271 Co-Teaching →Contributions
1 November 2018
- 00:5400:54, 1 November 2018 diff hist 0 DeepVO Towards end to end visual odometry with deep RNN →Training and Optimization
- 00:4900:49, 1 November 2018 diff hist +109 DeepVO Towards end to end visual odometry with deep RNN →Introduction
- 00:3000:30, 1 November 2018 diff hist +314 DeepVO Towards end to end visual odometry with deep RNN →Conclusions
- 00:1700:17, 1 November 2018 diff hist +471 DeepVO Towards end to end visual odometry with deep RNN →Training and Optimization
30 October 2018
- 23:2623:26, 30 October 2018 diff hist +14 Synthesizing Programs for Images usingReinforced Adversarial Learning →MUJOCO SCENES
- 23:2623:26, 30 October 2018 diff hist 0 N File:figure9 mcmc.PNG No edit summary current
- 23:2523:25, 30 October 2018 diff hist −11 Synthesizing Programs for Images usingReinforced Adversarial Learning →MUJOCO SCENES
- 23:1923:19, 30 October 2018 diff hist 0 File:Figure99.png X832zhan uploaded a new version of File:Figure99.png current
- 23:1723:17, 30 October 2018 diff hist +14 Synthesizing Programs for Images usingReinforced Adversarial Learning →MUJOCO SCENES
- 23:1423:14, 30 October 2018 diff hist 0 Synthesizing Programs for Images usingReinforced Adversarial Learning →MUJOCO SCENES
- 23:1423:14, 30 October 2018 diff hist +1 Synthesizing Programs for Images usingReinforced Adversarial Learning →MUJOCO SCENES
- 23:1323:13, 30 October 2018 diff hist 0 N File:Figure99.png No edit summary
- 23:1323:13, 30 October 2018 diff hist +1,209 Synthesizing Programs for Images usingReinforced Adversarial Learning →MUJOCO SCENES
- 22:1922:19, 30 October 2018 diff hist +4 Synthesizing Programs for Images usingReinforced Adversarial Learning →Conditional generation:
- 22:1822:18, 30 October 2018 diff hist +314 Synthesizing Programs for Images usingReinforced Adversarial Learning →Conditional generation:
29 October 2018
- 22:1122:11, 29 October 2018 diff hist 0 N File:fig8.PNG No edit summary current
- 22:1122:11, 29 October 2018 diff hist +858 End to end Active Object Tracking via Reinforcement Learning →Results
- 20:5420:54, 29 October 2018 diff hist +111 End to end Active Object Tracking via Reinforcement Learning →Environment Augmentation
- 20:4020:40, 29 October 2018 diff hist +3 End to end Active Object Tracking via Reinforcement Learning No edit summary
- 20:3020:30, 29 October 2018 diff hist +1 End to end Active Object Tracking via Reinforcement Learning →A3C Algorithm
- 20:2920:29, 29 October 2018 diff hist +276 End to end Active Object Tracking via Reinforcement Learning →A3C Algorithm
- 19:5319:53, 29 October 2018 diff hist +105 End to end Active Object Tracking via Reinforcement Learning →Approach
4 October 2018
2 October 2018
- 14:0014:00, 2 October 2018 diff hist +6 stat946F18 →Paper presentation
- 14:0014:00, 2 October 2018 diff hist +1 stat946F18 →Paper presentation
- 14:0014:00, 2 October 2018 diff hist +116 stat946F18 →Paper presentation
- 13:0413:04, 2 October 2018 diff hist +12 stat946F18 →Paper presentation