Ambiguous binary representation in multilayer neural networks
Resource
Neural Networks, 1995. Proceedings., IEEE International Conference on
Journal
IEEE International Conference on Neural Networks, 1995
Journal Issue
1
Pages
379-384
Date Issued
1995-12
Date
1995-12
Author(s)
Liou, Cheng-Yuan
Yu, Wen-Jen
DOI
N/A
Abstract
We develop a side direction process to assist the back propagation learning algorithm to resolve the premature saturation problem. To build this side process, we explore the idea of unfaithful representation which has been introduced in the tiling algorithm. The algorithm may grow to an unpredictably large network for a given pattern set. This unfaithful representation is equivalent to the ambiguous binary representation. Binary numbers are used to represent the output binary vectors of hidden layers. More training patterns of different classes map to the same binary number, more patterns are misclassified. Besides, the presence of ambiguous binary representations is also an important pointer of when and where we should add a new hidden neuron to the multilayer perceptron. In this work, we explain the happening of ambiguous binary representation and develop a method to alleviate it. Using this method, both the number of ambiguous binary representations and the backpropagation learning time are drastically reduced.
Type
conference paper
File(s)![Thumbnail Image]()
Loading...
Name
00488129.pdf
Size
37.38 KB
Format
Adobe PDF
Checksum
(MD5):06474753b9f7fa745c642d44af0c4fff