Journal ArticleDOI
Sequential processing by overlap and fatigue of memories
TLDR
The basic features of the model to be described here are a 100% interconnected network with symmetrical weights, a continuously changing activation of the nodes between 0 and 1, a "fatigue" of the activability of nodes as a function of time and current activation, a Hebbian-like learning rule, and a strongly negative starting weight of the connections.About:
This article is published in Neural Networks.The article was published on 1988-01-01. It has received 27 citations till now.read more
Citations
More filters
Journal ArticleDOI
A solution to the tag-assignment problem for neural networks
TL;DR: In this article, an attentional tag-assignment model was proposed to correct illusory conjunctions in a purely parallel neural network, where one component of the model extracts pooled features and another provides attentional tags that correct the errors of illusORY conjunctions.
Journal ArticleDOI