We often think of Momentum as a means of dampening oscillations and speeding up the iterations, leading to faster convergence. But it has other interesting behavior. It allows a larger range of step-sizes to be used, and creates its own oscillations. What is going on?
From Yann LeCun's facebook page:
"Wonderful position paper by Max Welling entitled
"Are Machine Learning and Statistics Complementary?"
presented at the Rountable Discussion at the 6th…Read More
The paper presents he first deep learning model to successfully learn control policies directly from high-dimensional sensory input using reinforcement learning. It's a must read for AI scientists
In this paper, the author use reinforcement learning to study intelligent agents. Each reinforcement learning agent can incrementally learn an efficient decision policy over a state space by trial and error where the…Read More
Abstract:
"There has been a recent explosion in the capabilities of game-playing artificial intelligence. Many classes of RL tasks, from Atari games to motor control to board games, are now solvable…Read More
"To address these issues of limited time and diagnostic variability, we are investigating how deep learning can be applied to digital pathology, by creating an automated detection algorithm that can naturally complement…Read More
