Linear Algebra Approach to Neural Associative Memories and Noise performance of Neural Classifiers

Authors:
Vladimir Cherkassky;Karen Fassett;Nikolaos Vassilas
Affiliations:
-;-;-
Venue:
IEEE Transactions on Computers - Special issue on artificial neural networks
Year:
1991

Citing 8
Cited 5

A Quantitative Comparison of the Performance of Three Discrete Distributed Associative Memory Models

IEEE Transactions on Computers
Distributed and Fault-Tolerant Computation for Retrieval Tasks Using Distributed Associative Memories

IEEE Transactions on Computers - Fault-Tolerant Computing
Adaptive pattern recognition and neural networks

Adaptive pattern recognition and neural networks
Self-organization and associative memory: 3rd edition

Self-organization and associative memory: 3rd edition
The appeal of parallel distributed processing

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Perceptrons

Neurocomputing: foundations of research
Introduction to matrix analysis (2nd ed.)

Introduction to matrix analysis (2nd ed.)
Performance of neural associative memories for character recognition and associative database retrieval

Performance of neural associative memories for character recognition and associative database retrieval

Spelling correction for the telecommunications network for the deaf

Communications of the ACM
Techniques for automatically correcting words in text

ACM Computing Surveys (CSUR)
Noise Performance of Linear Associative Memories

IEEE Transactions on Pattern Analysis and Machine Intelligence
Data Representation for Diagnostic Neural Networks

IEEE Expert: Intelligent Systems and Their Applications
Improving the classification performance of optimal linear associative memory in the presence of outliers

IWANN'13 Proceedings of the 12th international conference on Artificial Neural Networks: advances in computational intelligence - Volume Part I

Quantified Score

Hi-index	0.02

Visualization

Abstract

The authors present an analytic evaluation of saturation and noise performance for a large class of associative memories based on matrix operations. The importance of using standard linear algebra techniques for evaluating noise performance of associative memories is emphasized. The authors present a detailed comparative analysis of the correlation matrix memory and the generalized inverse memory construction rules for auto-associative memory and neural classifiers. Analytic results for the noise performance of neural classifiers that can store several prototypes in one class are presented. The analysis indicates that for neural classifiers the simple correlation matrix memory provides better noise performance than the more complex generalized inverse memory.