大工至善|大学至真分享 http://blog.sciencenet.cn/u/lcj2212916



已有 247 次阅读 2019-11-15 14:14 |系统分类:科研笔记|文章来源:转载

本文为美国加州理工学院(作者:Timothy X Brown)的博士论文,共109页。








A neural network is a highly interconnectedset of simple processors. The many connections allow information to travelrapidly through the network, and due to their simplicity, many processors inone network are feasible. Together these properties imply that we can buildefficient massively parallel machines using neural networks. The primaryproblem is how do we specify the interconnections in a neural network. Thevarious approaches developed so far such as outer product, learning algorithm,or energy function suffer from the following deficiencies: longtraining/specification times; not guaranteed to work on all inputs; requiresfull connectivity.

Alternatively we discuss methods of usingthe topology and constraints of the problems themselves to design the topologyand connections of the neural solution. We define several usefulcircuits—generalizations of the Winner-Take-All circuit— that allows us toincorporate constraints using feedback in a controlled manner. These circuitsare proven to be stable, and to only converge on valid states. We use theHopfield electronic model since this is close to an actual implementation. Wealso discuss methods for incorporating these circuits into larger systems,neural and nonneural. By exploiting regularities in our definition, we canconstruct efficient networks.

To demonstrate the methods, we look tothree problems from communications. We first discuss two applications toproblems from circuit switching; finding routes in large multistage switches,and the call rearrangement problem. These show both, how we can use manyneurons to build massively parallel machines, and how the Winner-Take-Allcircuits can simplify our designs. Next we develop a solution to the contentionarbitration problem of high-speed packet switches. We define a useful class ofswitching networks and then design a neural network to solve the contentionarbitration problem for this class. Various aspects of the neural network/switchsystem are analyzed to measure the queueing performance of this method. Usingthe basic design, a feasible architecture for a large (1024-input) ATM packetswitch is presented. Using the massive parallelism of neural networks, we canconsider algorithms that were previously computationally v unattainable. Thesenow viable algorithms lead us to new perspectives on switch design.



1. 引言

2. 神经网络设计

3. 电路交换网络的控制

4. Banyan网络控制器

5. 后记





该博文允许注册用户评论 请点击登录 评论 (0 个评论)


Archiver|手机版|科学网 ( 京ICP备14006957 )

GMT+8, 2019-12-10 15:18

Powered by ScienceNet.cn

Copyright © 2007- 中国科学报社