More Consideration for the Perceptron

TL;DR

This paper introduces the gated perceptron, an enhanced model that captures feature interactions through multiplicative inputs, improving classification and regression on complex datasets while maintaining simplicity.

Contribution

The paper presents the gated perceptron, a novel extension of the perceptron that incorporates multiplicative interactions to better handle non-linear data.

Findings

Gated perceptron generates more distinct decision regions.

It performs competitively with state-of-the-art classifiers.

Effective in both linear and non-linear tasks.

Abstract

In this paper, we introduce the gated perceptron, an enhancement of the conventional perceptron, which incorporates an additional input computed as the product of the existing inputs. This allows the perceptron to capture non-linear interactions between features, significantly improving its ability to classify and regress on complex datasets. We explore its application in both linear and non-linear regression tasks using the Iris dataset, as well as binary and multi-class classification problems, including the PIMA Indian dataset and Breast Cancer Wisconsin dataset. Our results demonstrate that the gated perceptron can generate more distinct decision regions compared to traditional perceptrons, enhancing its classification capabilities, particularly in handling non-linear data. Performance comparisons show that the gated perceptron competes with state-of-the-art classifiers while maintaining a simple architecture.