Explaining the Neuroevolution of Fighting Creatures Through Virtual fMRI
- 2 January 2023
- journal article
- research article
- Published by MIT Press in Artificial Life
- Vol. 29 (1), 66-93
- https://doi.org/10.1162/artl_a_00389
Abstract
While interest in artificial neural networks (ANNs) has been renewed by the ubiquitous use of deep learning to solve high-dimensional problems, we are still far from general artificial intelligence. In this article, we address the problem of emergent cognitive capabilities and, more crucially, of their detection, by relying on co-evolving creatures with mutable morphology and neural structure. The former is implemented via both static and mobile structures whose shapes are controlled by cubic splines. The latter uses ESHyperNEAT to discover not only appropriate combinations of connections and weights but also to extrapolate hidden neuron distribution. The creatures integrate low-level perceptions (touch/pain proprioceptors, retina-based vision, frequency-based hearing) to inform their actions. By discovering a functional mapping between individual neurons and specific stimuli, we extract a high-level module-based abstraction of a creature’s brain. This drastically simplifies the discovery of relationships between naturally occurring events and their neural implementation. Applying this methodology to creatures resulting from solitary and tag-team co-evolution showed remarkable dynamics such as range-finding and structured communication. Such discovery was made possible by the abstraction provided by the modular ANN which allowed groups of neurons to be viewed as functionally enclosed entities.This publication has 33 references indexed in Scilit:
- Artificial Evolution of Plastic Neural Networks: A Few Key ConceptsPublished by Springer Science and Business Media LLC ,2014
- On the Relationships between Generative Encodings, Regularity, and Learning Abilities when Evolving Plastic Artificial Neural NetworksPLOS ONE, 2013
- An Enhanced Hypercube-Based Encoding for Evolving the Placement, Density, and Connectivity of NeuronsArtificial Life, 2012
- Measurement of the Top-Quark Mass with Dilepton Events Selected Using Neuroevolution at CDFPhysical Review Letters, 2009
- A Hypercube-Based Encoding for Evolving Large-Scale Neural NetworksArtificial Life, 2009
- Compositional pattern producing networks: A novel abstraction of developmentGenetic Programming and Evolvable Machines, 2007
- On the Use of Virtual Animals with Artificial Fear in Virtual EnvironmentsNew Generation Computing, 2007
- Modeling Emotion-Influenced Social Behavior for Intelligent Virtual AgentsLecture Notes in Computer Science, 2007
- Evolving Neural Networks through Augmenting TopologiesEvolutionary Computation, 2002
- Evolving 3D Morphology and Behavior by CompetitionArtificial Life, 1994