Document Type
Report
Date
7-1980
Keywords
Neural learning
Language
English
Disciplines
Computer Sciences
Description/Abstract
This paper addresses the relationship between the number of hidden layer nodes in a neural network, the complexity of a multi-class discrimination problem, and the number of samples needed for effective learning. Bounds are given for the latter. We show that Ω(min(d,n).M) boundary samples are required for successful classification of M clusters of samples using a 2 hidden layer neural network with d-dimensional inputs and n nodes in the first hidden layer.
Recommended Citation
Mehrotra, Kishan G.; Mohan, Chilukuri K.; and Ranka, Sanjay, "Bounds on the Number of Samples Needed for Neural Learning" (1980). Electrical Engineering and Computer Science - Technical Reports. 94.
https://surface.syr.edu/eecs_techreports/94
Source
local
Additional Information
School of Information and Computer Science, Syracuse University, SU-CIS-90-20