Document Type

Report

Date

6-15-1993

Keywords

Algorithms & Architectures, Constructive & Pruning Algorithms

Language

English

Disciplines

Computer Sciences

Description/Abstract

We present a problem decomposition approach to reduce neural net training times. The basic idea is to train neural nets in parallel on marginal distributions obtained from the original distribution (via projection), and then reconstruct the original table from the marginals (via a procedure similar to the join operator in database theory). A function is said to be reconstructible, if it may be recovered without error from its projections. Most distributions are non-reconstructible. The main result of this paper is the Reconstruction theorem, which enables non-reconstructible functions to be expressed in terms of reconstructible ones, and thus facilitates the application of decomposition methods.

Additional Information

School of Computer and Information Science, Syracuse University, SU-CIS-93-28

Source

local

Share

COinS
 
 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.