We evaluate two broad classes of cognitive mechanisms that might support the learning of sequential patterns. According to the first, learning is based on the gradual accumulation...
Abstract. This paper proposes an account of the acquisition of grammatical relations using the basic concepts of connectionism and a construction-based theory of grammar. Many prev...
William C. Morris, Garrison W. Cottrell, Jeffrey L...
Abstract. Compared to normal learning algorithms, for example backpropagation, the optimal bounded ellipsoid (OBE) algorithm has some better properties, such as faster convergence,...
Abstract. Conventional artificial neural network models lack many physiological properties of the neuron. Current learning algorithms are more concerned to computational performanc...
Following Tesauro’s work on TD-Gammon, we used a 4000 parameter feed-forward neural network to develop a competitive backgammon evaluation function. Play proceeds by a roll of t...