On the potential for open-endedness in neural networks

12/12/2018
by   Nicholas Guttenberg, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/21/2018

Creativity and Artificial Intelligence: A Digital Art Perspective

This paper describes the application of artificial intelligence to the c...
research
07/27/2015

Requirements for Open-Ended Evolution in Natural and Artificial Systems

Open-ended evolutionary dynamics remains an elusive goal for artificial ...
research
07/20/2021

Evolutionary Innovation Viewed as Novel Physical Phenomena and Hierarchical Systems Building

In previous work I proposed a framework for thinking about open-ended ev...
research
06/12/2020

Open Questions in Creating Safe Open-ended AI: Tensions Between Control and Creativity

Artificial life originated and has long studied the topic of open-ended ...
research
02/01/2018

Machine learning and evolutionary techniques in interplanetary trajectory design

After providing a brief historical overview on the synergies between art...
research
12/21/2011

Passive and Driven Trends in the Evolution of Complexity

The nature and source of evolutionary trends in complexity is difficult ...
research
08/07/2023

Bridging Trustworthiness and Open-World Learning: An Exploratory Neural Approach for Enhancing Interpretability, Generalization, and Robustness

As researchers strive to narrow the gap between machine intelligence and...

Please sign up or login with your details

Forgot password? Click here to reset