Modeling neural networks in Scheme

Author:

Eilbert James L.1,Salter Richard M.2

Affiliation:

1. Department of Mathematics and Computer Sciences Drexel University Philadelphia, Pennsylvania 19104

2. Department of Mathematics Oberlin College Oberlin, Ohio 44074

Abstract

A system for simulating neural networks has been written in the LISP dialect, Scheme, using an object-oriented style of program ming, rather than the standard numerical techniques used in previous studies. Each node in the Scheme network represents either a neuron or a functional group of neurons, and can pass messages which trigger computations and actions in other nodes. The Scheme modeling approach overcomes two major problems inherent to the standard numerical approach. First, it provides a flexible environment for systematically studying the effects of perturbing a network's structure, response, or updating param eters. In fact, the Scheme system can recreate any previously studied neural network. Second, it allows the construction of hierarchical networks with several interacting levels. This system can handle hierarchical organization in a natural way, because a single node in a Scheme network can contain a model of an entire lower level of neural processing. The implementation of neural networks with hierarchical structure is significant because recent biological data suggests that this is the architecture which supports human cognition.

Publisher

SAGE Publications

Subject

Computer Graphics and Computer-Aided Design,Modelling and Simulation,Software

Reference32 articles.

1. Competition and Cooperation in Neural Nets

2. Distinctive features, categorical perception, and probability learning: Some applications of a neural model.

3. Bloom, F.E. "Chemical integrative process in the central nervous system." In: The neuro-sciences : Forth study program. ( F. O. Schmitt and F G. Worden, eds.) MIT Press, Cambridge, Mass. (1979), 51-58.

4. A theory for the acquisition and loss of neuron specificity in visual cortex

Cited by 11 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

1. A framework for Integrating Artificial Intelligence and Simulation;Artificial Intelligence Review;1994

2. Cardiac Electrophysiological Experiments in Numero, Part I: Concepts and Strategies of Mathematical and Computer Models;Pacing and Clinical Electrophysiology;1991-10

3. Syntactic modeling and simulation;SIMULATION;1990-06

4. Bibliography;Object-Oriented Simulation with Hierarchical, Modular Models;1990

5. Knowledge-based environment for investigating multicomputer architectures;Information and Software Technology;1989-12

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3