Affiliation:
1. Dipartimento di Sistemi e lnformatica, Via di S. Marta, 3-50139 Firenze, Italy
Abstract
In this paper, we investigate the capabilities of local feedback multilayered networks, a particular class of recurrent networks, in which feedback connections are only allowed from neurons to themselves. In this class, learning can be accomplished by an algorithm that is local in both space and time. We describe the limits and properties of these networks and give some insights on their use for solving practical problems.
Subject
Cognitive Neuroscience,Arts and Humanities (miscellaneous)
Cited by
131 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献