The dynamical behavior and the stability properties of fixed points in a feedback auto-associative memory are investigated. The proposed structure encompasses a multi-layer percep...
Mahmood Amiri, Sohrab Saeb, Mohammad Javad Yazdanp...
Reinforcement learning problems are commonly tackled with temporal difference methods, which use dynamic programming and statistical sampling to estimate the long-term value of ta...
In this paper we introduce Ant-Q, a family of algorithms which present many similarities with Q-learning (Watkins, 1989), and which we apply to the solution of symmetric and asymm...
Abstract. Inspired on psycholinguistics and neuroscience, a symbolicconnectionist hybrid system called θ-Pred (Thematic Predictor for natural language) is proposed, designed to re...
Abstract— Cognitive control - the ability to produce appropriate behavior in complex situations - is a fundamental aspect of intelligence. It is increasingly evident that this co...