Binary output layer of feedforward neural networks for solving multi-class classification problems

TL;DR

This paper introduces a binary output layer design for multi-class neural network classification that reduces the number of output nodes while maintaining performance, compared to the traditional one-to-one approach.

Contribution

The paper proposes a novel binary approach for output layer design in multi-class neural networks, reducing output nodes needed.

Findings

Binary approach uses fewer output nodes than traditional method.

Numerical experiments show comparable performance to one-to-one approach.

Binary approach is effective for classes r in the range (2^(q-1), 2^q].

Abstract

Considered in this short note is the design of output layer nodes of feedforward neural networks for solving multi-class classification problems with r (bigger than or equal to 3) classes of samples. The common and conventional setting of output layer, called "one-to-one approach" in this paper, is as follows: The output layer contains r output nodes corresponding to the r classes. And for an input sample of the i-th class, the ideal output is 1 for the i-th output node, and 0 for all the other output nodes. We propose in this paper a new "binary approach": Suppose r is (2^(q minus 1), 2^q] with q bigger than or equal to 2, then we let the output layer contain q output nodes, and let the ideal outputs for the r classes be designed in a binary manner. Numerical experiments carried out in this paper show that our binary approach does equally good job as, but uses less output nodes than, the traditional one-to-one approach.