Identification of Low Frequency Patterns in Backpropagation Neural Networks

From Tetherless World Wiki

Jump to: navigation, search

Citation: Lucila Ohno-Machado. (1994) Identification of Low Frequency Patterns in Backpropagation Neural Networks. In KSL-94-29, November,1994.

Publication techreport ( Edit )
type Technical Report
bibtype techreport
Bibtex basics
author Lucila Ohno-Machado
title Identification of Low Frequency Patterns in Backpropagation Neural Networks
number KSL-94-29
institution Knowledge Systems, AI Laboratory
year 1994
month November
Bibtex more
note Updated November 1994. Medical Computer Science
Access Paper
abstract Although neural networks have been widely applied to medical problems in recent years, their applicability has been limited for a variety of reasons. One of these barriers has been the inability to discriminate rare classes of solutions (i.e., the identification of categories that are infrequent). In this article, I demonstrate that a system of hierarchical neural networks (HNN) can overcome the problem of recognizing low frequency patterns, and therefore can improve the prediction power of neural-network systems. HNN are designed according to a divide-and-conquer approach: Triage networks are able to discriminate supersets that contain the infrequent pattern, and these supersets are then used by Specialized networks, which discriminate the infrequent pattern from the other ones in the superset. The supersets that are discriminated by the Triage networks are based on pattern similarity. The application of multilayered neural networks in more than one step allows the prior probability of a given pattern to increase at each step, provided that the predictive power of the network at the previous level is high. The method has been applied to one artificial set and one real set of data. In the artificial set, the distribution of the patterns was known and no noise was present. In this experiment, he HNN provided better discrimination than a standard neural network for all classes. In a real data set of nine thousand patients who were suspected of having thyroid disorders, the HNN also provided higher sensitivity than its corresponding standard neural network (without a corresponding decay in specificity) given the same time constraints. I discuss the reasons why the sensitivity achieved by systems of divide-and-conquer hierarchical neural networks is superior to that of non-hierarchical neural network models, the conditions in which the algorithm should be applied, potential improvements, and current limitations.

KSL Technical Report ID: KSL-94-29
Facts about Identification of Low Frequency Patterns in Backpropagation Neural NetworksRDF feed
Abstract Although neural networks have been widely … Although neural networks have been widely applied to medical problems in recent years, their applicability has been limited for a variety of reasons. One of these barriers has been the inability to discriminate rare classes of solutions (i.e., the identification of categories that are infrequent). In this article, I demonstrate that a system of hierarchical neural networks (HNN) can overcome the problem of recognizing low frequency patterns, and therefore can improve the prediction power of neural-network systems. HNN are designed according to a divide-and-conquer approach: Triage networks are able to discriminate supersets that contain the infrequent pattern, and these supersets are then used by Specialized networks, which discriminate the infrequent pattern from the other ones in the superset. The supersets that are discriminated by the Triage networks are based on pattern similarity. The application of multilayered neural networks in more than one step allows the prior probability of a given pattern to increase at each step, provided that the predictive power of the network at the previous level is high. The method has been applied to one artificial set and one real set of data. In the artificial set, the distribution of the patterns was known and no noise was present. In this experiment, he HNN provided better discrimination than a standard neural network for all classes. In a real data set of nine thousand patients who were suspected of having thyroid disorders, the HNN also provided higher sensitivity than its corresponding standard neural network (without a corresponding decay in specificity) given the same time constraints. I discuss the reasons why the sensitivity achieved by systems of divide-and-conquer hierarchical neural networks is superior to that of non-hierarchical neural network models, the conditions in which the algorithm should be applied, potential improvements, and current limitations. ial improvements, and current limitations.
Author Lucila Ohno-Machado  +
Bibtype techreport  +
Has author Lucila Ohno-Machado  +
Has identifier KSL-94-29  +
Has publishing details November,1994  +
Has title Identification of Low Frequency Patterns in Backpropagation Neural Networks  +
Has where published KSL-94-29  +
Has year 1994  +
Institution Knowledge Systems, AI Laboratory  +
Ksl tr id KSL-94-29  +
Month November  +
Note Updated November 1994. Medical Computer Science
Number KSL-94-29  +
Process note NO  +
Title Identification of Low Frequency Patterns in Backpropagation Neural Networks  +
Year 1994  +
Retrieved from "http://tw.rpi.edu/wiki/Identification_of_Low_Frequency_Patterns_in_Backpropagation_Neural_Networks"
Personal tools