Learning Enhancement of CNNs via Separation Index Maximizing at the First Convolutional Layer

TL;DR

This paper introduces a new learning enhancement method for CNNs that maximizes the Separation Index at the first convolutional layer, improving classification performance across various datasets.

Contribution

It proposes a novel strategy to optimize the first CNN layer by maximizing the Separation Index, enhancing learning efficiency and accuracy.

Findings

Improved classification accuracy on multiple datasets.

Effective enhancement of CNN learning through SI maximization.

Consistent performance gains across tested models.

Abstract

In this paper, a straightforward enhancement learning algorithm based on Separation Index (SI) concept is proposed for Convolutional Neural Networks (CNNs). At first, the SI as a supervised complexity measure is explained its usage in better learning of CNNs for classification problems illustrate. Then, a learning strategy proposes through which the first layer of a CNN is optimized by maximizing the SI, and the further layers are trained through the backpropagation algorithm to learn further layers. In order to maximize the SI at the first layer, A variant of ranking loss is optimized by using the quasi least square error technique. Applying such a learning strategy to some known CNNs and datasets, its enhancement impact in almost all cases is demonstrated.