User contributions for Lwali
Jump to navigation
Jump to search
29 November 2018
- 16:1516:15, 29 November 2018 diff hist +90 DON'T DECAY THE LEARNING RATE , INCREASE THE BATCH SIZE →STOCHASTIC GRADIENT DESCENT AND CONVEX OPTIMIZATION
- 16:0616:06, 29 November 2018 diff hist +173 Fix your classifier: the marginal value of training the last weight layer →Language Modelling
- 15:4515:45, 29 November 2018 diff hist +178 learn what not to learn →Action Elimination
- 12:5612:56, 29 November 2018 diff hist +2 CapsuleNets →Dynamic Routing
- 12:3112:31, 29 November 2018 diff hist −5 DETECTING STATISTICAL INTERACTIONS FROM NEURAL NETWORK WEIGHTS →Related Work