# On the potential for open-endedness in neural networks

## TL;DR

This paper explores how principles from evolution can inform machine learning to foster open-endedness, aiming to create systems with increasing diversity and complexity through interdisciplinary insights.

## Contribution

It bridges evolutionary and machine learning approaches by analyzing barriers to open-endedness and proposing solutions transferable between the two fields.

## Key findings

- Identifies key barriers like diversity collapse and saturation in both approaches.
- Shows how evolutionary solutions can be adapted for machine learning.
- Suggests new methods for analyzing and overcoming open-endedness barriers.

## Abstract

Natural evolution gives the impression of leading to an open-ended process of increasing diversity and complexity. If our goal is to produce such open-endedness artificially, this suggests an approach driven by evolutionary metaphor. On the other hand, techniques from machine learning and artificial intelligence are often considered too narrow to provide the sort of exploratory dynamics associated with evolution. In this paper, we hope to bridge that gap by reviewing common barriers to open-endedness in the evolution-inspired approach and how they are dealt with in the evolutionary case - collapse of diversity, saturation of complexity, and failure to form new kinds of individuality. We then show how these problems map onto similar issues in the machine learning approach, and discuss how the same insights and solutions which alleviated those barriers in evolutionary approaches can be ported over. At the same time, the form these issues take in the machine learning formulation suggests new ways to analyze and resolve barriers to open-endedness. Ultimately, we hope to inspire researchers to be able to interchangeably use evolutionary and gradient-descent-based machine learning methods to approach the design and creation of open-ended systems.