2 papers
cs.LG2020
SPLASH: Learnable Activation Functions for Improving Accuracy and Adversarial Robustness
Mohammadamin Tavakoli, Forest Agostinelli, Pierre Baldi
We introduce SPLASH units, a class of learnable activation functions shown to simultaneously improve the accuracy of deep neural networks while also improving their robustness to a…
cs.AI2018
Solving the Rubik's Cube Without Human Knowledge
Stephen McAleer, Forest Agostinelli, Alexander Shmakov +1
A generally intelligent agent must be able to teach itself how to solve problems in complex domains with minimal human supervision. Recently, deep reinforcement learning algorithms…