# Generative NeuroEvolution for Deep Learning

Source: [Generative NeuroEvolution for Deep Learning](<https://www.sota2.com/research/paper/68fa61291e209131ce9f2d20>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T19:53:34.667Z

Authors: Phillip Verbancsics, Josh Harguess

Published: 2013-12-18T22:14:31.000Z

## Abstract

An important goal for the machine learning (ML) community is to create approaches that can learn solutions with human-level capability. One domain where humans have held a significant advantage is visual processing. A significant approach to addressing this gap has been machine learning approaches that are inspired from the natural systems, such as artificial neural networks (ANNs), evolutionary computation (EC), and generative and developmental systems (GDS). Research into deep learning has demonstrated that such architectures can achieve performance competitive with humans on some visual tasks; however, these systems have been primarily trained through supervised and unsupervised learning algorithms. Alternatively, research is showing that evolution may have a significant role in the development of visual systems. Thus this paper investigates the role neuro-evolution (NE) can take in deep learning. In particular, the Hypercube-based NeuroEvolution of Augmenting Topologies is a NE approach that can effectively learn large neural structures by training an indirect encoding that compresses the ANN weight pattern as a function of geometry. The results show that HyperNEAT struggles with performing image classification by itself, but can be effective in training a feature extractor that other ML approaches can learn from. Thus NeuroEvolution combined with other ML methods provides an intriguing area of research that can replicate the processes in nature.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1312.5355>)

[PDF](<https://arxiv.org/pdf/1312.5355.pdf>)
