Symbolic mapping of neurons in feedforward networks

Authors:
Ishwar K. Sethi;Jae H. Yoo
Affiliations:
-;-
Venue:
Pattern Recognition Letters
Year:
1996

Citing 7
Cited 1

Connectionist expert systems

Communications of the ACM
Connectionist learning procedures

Artificial Intelligence
Logical versus analogical or symbolic versus connectionist or neat versus scruffy

AI Magazine
Extracting Refined Rules from Knowledge-Based Neural Networks

Machine Learning
A fast parallel algorithm for thinning digital patterns

Communications of the ACM
Logic Minimization Algorithms for VLSI Synthesis

Logic Minimization Algorithms for VLSI Synthesis
Rule learning by searching on adapted nets

AAAI'91 Proceedings of the ninth National conference on Artificial intelligence - Volume 2

Data mining: an introducation

Data mining for design and manufacturing

Quantified Score

Hi-index	0.10

Visualization

Abstract

It is common to view multiple-layer feedforward neural networks as black boxes since the knowledge embedded in the connection weights of these networks is generally considered incomprehensible. This paper proposes a solution to this deficiency of neural networks by suggesting a mapping procedure for converting the weights of a neuron into a symbolic representation and demonstrating its use towards understanding the internal representation and the input-output mapping learned by a feedforward neural network. Several examples are presented to illustrate the proposed symbolic mapping of neurons.