Training of CC4 Neural Network with Spread Unary Coding

TL;DR

This paper introduces a modified CC4 neural network training algorithm that uses spread unary inputs, demonstrating robustness in classification tasks and relevance to biological data representation.

Contribution

The paper adapts the CC4 algorithm to incorporate spread unary coding, a novel approach linking neural network training with biological data encoding.

Findings

Misclassification rate is insensitive to the radius of generalization.

Modified CC4 performs well on pattern classification tasks.

Spread unary coding is effective for biological data representation.

Abstract

This paper adapts the corner classification algorithm (CC4) to train the neural networks using spread unary inputs. This is an important problem as spread unary appears to be at the basis of data representation in biological learning. The modified CC4 algorithm is tested using the pattern classification experiment and the results are found to be good. Specifically, we show that the number of misclassified points is not particularly sensitive to the chosen radius of generalization.