It is widely accepted that the use of more compact representations than lookup tables is crucial to scaling reinforcement learning (RL) algorithms to real-world problems. Unfortun...
Satinder P. Singh, Tommi Jaakkola, Michael I. Jord...
Understanding knowledge representations in neural nets has been a difficult problem. Principal components analysis (PCA) of contributions (products of sending activations and conn...
Thomas R. Shultz, Yuriko Oshima-Takane, Yoshio Tak...
Experiments were performed to reveal some of the computational properties of the human motor memory system. We show that as humans practice reaching movements while interacting wi...
Reza Shadmehr, Tom Brashers-Krug, Ferdinando A. Mu...
Each yearpeoplespendahugeamountoftimetyping. Thetextpeopletype typically contains a tremendousamount of redundancy due to predictable word usage patterns and the text's struc...
We present a statistical method that PAC learns the class of stochastic perceptrons with arbitrary monotonic activation function and weights wi {-1, 0, +1} when the probability d...