Towards Deep Representation Learning with Genetic Programming

TL;DR

This paper introduces a genetic programming-based autoencoder that transforms large-scale datasets into compact representations, potentially rivaling deep neural networks in performance.

Contribution

It presents a novel GP-driven autoencoder approach for dataset compression and feature transformation in machine learning tasks.

Findings

Preliminary tests on image datasets show promising results.

The method can produce compact representations of data.

Potential to compete with deep neural networks.

Abstract

Genetic Programming (GP) is an evolutionary algorithm commonly used for machine learning tasks. In this paper we present a method that allows GP to transform the representation of a large-scale machine learning dataset into a more compact representation, by means of processing features from the original representation at individual level. We develop as a proof of concept of this method an autoencoder. We tested a preliminary version of our approach in a variety of well-known machine learning image datasets. We speculate that this method, used in an iterative manner, can produce results competitive with state-of-art deep neural networks.