On the Relationships between Generative Encodings, Regularity, and Learning Abilities when Evolving Plastic Artificial Neural Networks

Tonelli, Paul; Mouret, Jean-Baptiste

doi:10.1371/journal.pone.0079138

Cited by 27 publications

(23 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Lastly, a recent technique showed that the regular patterns produced by a generative encoding, such as Hyper-NEAT, aids the learning capabilities of networks [34]. We will combine our method with intra-life learning algorithms to investigate whether learning is improved when it occurs in structurally organized neural networks.…”

Section: Future Workmentioning

confidence: 99%

Evolving neural networks that are both modular and regular

Huizinga

Clune

Mouret

2014

Proceedings of the 2014 Annual Conference on Genetic and Evolutionary Computation

Self Cite

View full text Add to dashboard Cite

One of humanity's grand scientific challenges is to create artificially intelligent robots that rival natural animals in intelligence and agility. A key enabler of such animal complexity is the fact that animal brains are structurally organized in that they exhibit modularity and regularity, amongst other attributes. Modularity is the localization of function within an encapsulated unit. Regularity refers to the compressibility of the information describing a structure, and typically involves symmetries and repetition. These properties improve evolvability, but they rarely emerge in evolutionary algorithms without specific techniques to encourage them. It has been shown that (1) modularity can be evolved in neural networks by adding a cost for neural connections and, separately, (2) that the HyperNEAT algorithm produces neural networks with complex, functional regularities. In this paper we show that adding the connection cost technique to HyperNEAT produces neural networks that are significantly more modular, regular, and higher performing than Hyper-NEAT without a connection cost, even when compared to a variant of HyperNEAT that was specifically designed to encourage modularity. Our results represent a stepping stone towards the goal of producing artificial neural networks that share key organizational properties with the brains of natural animals.

show abstract

Section: Future Workmentioning

confidence: 99%

Evolving neural networks that are both modular and regular

Huizinga

Clune

Mouret

2014

Proceedings of the 2014 Annual Conference on Genetic and Evolutionary Computation

Self Cite

View full text Add to dashboard Cite

show abstract

“…Valsalam et al concluded that their prenatal stage implemented a form of bias on the space of neural models, which could be adjusted by evolution to adapt the particular network to the problem at hand. A more recent study by Tonelli and Mouret also shows that a combination of development (via map-based and HyperNEAT-like encodings) and plasticity can lead to improved learning efficacy, which they attribute to the increased propensity toward the generation of symmetric networks [277] (see also Chap. 9).…”

Section: Epigenetic Simulationmentioning

confidence: 94%

Artificial Neurogenesis: An Introduction and Selective Review

Kowaliw

Bredèche

Chevallier³

et al. 2014

Growing Adaptive Machines

View full text Add to dashboard Cite

International audienceIn this introduction and review—like in the book which follows—we explore the hypothesis that adaptive growth is a means of producing brain-like machines. The emulation of neural development can incorporate desirable characteristics of natural neural systems into engineered designs. The introduction begins with a review of neural development and neural models. Next, artificial development— the use of a developmentally-inspired stage in engineering design—is introduced. Several strategies for performing this " meta-design " for artificial neural systems are reviewed. This work is divided into three main categories: bio-inspired representations ; developmental systems; and epigenetic simulations. Several specific network biases and their benefits to neural network design are identified in these contexts. In particular, several recent studies show a strong synergy, sometimes interchange-ability, between developmental and epigenetic processes—a topic that has remained largely under-explored in the literature

show abstract

“…One advantage of learning is that it is targeted, whereas mutation is random. The effectiveness of concurrently evolving direct and indirect encodings to address irregular problems might be reproduced or augmented by allowing learning to take place during fitness evaluation [42]. A key difference between Offset-HybrID and learning is that patterns within Offset-HybrID’s directly encoded genome are inherited by children while learned patterns are not usually passed on by a genome.…”

Section: Future Workmentioning

confidence: 99%

Improving HybrID: How to best combine indirect and direct encoding in evolutionary algorithms

Helms

Clune

2017

PLoS ONE

View full text Add to dashboard Cite

Many challenging engineering problems are regular, meaning solutions to one part of a problem can be reused to solve other parts. Evolutionary algorithms with indirect encoding perform better on regular problems because they reuse genomic information to create regular phenotypes. However, on problems that are mostly regular, but contain some irregularities, which describes most real-world problems, indirect encodings struggle to handle the irregularities, hurting performance. Direct encodings are better at producing irregular phenotypes, but cannot exploit regularity. An algorithm called HybrID combines the best of both: it first evolves with indirect encoding to exploit problem regularity, then switches to direct encoding to handle problem irregularity. While HybrID has been shown to outperform both indirect and direct encoding, its initial implementation required the manual specification of when to switch from indirect to direct encoding. In this paper, we test two new methods to improve HybrID by eliminating the need to manually specify this parameter. Auto-Switch-HybrID automatically switches from indirect to direct encoding when fitness stagnates. Offset-HybrID simultaneously evolves an indirect encoding with directly encoded offsets, eliminating the need to switch. We compare the original HybrID to these alternatives on three different problems with adjustable regularity. The results show that both Auto-Switch-HybrID and Offset-HybrID outperform the original HybrID on different types of problems, and thus offer more tools for researchers to solve challenging problems. The Offset-HybrID algorithm is particularly interesting because it suggests a path forward for automatically and simultaneously combining the best traits of indirect and direct encoding.

show abstract

On the Relationships between Generative Encodings, Regularity, and Learning Abilities when Evolving Plastic Artificial Neural Networks

Cited by 27 publications

References 58 publications

Evolving neural networks that are both modular and regular

Evolving neural networks that are both modular and regular

Artificial Neurogenesis: An Introduction and Selective Review

Improving HybrID: How to best combine indirect and direct encoding in evolutionary algorithms

Contact Info

Product

Resources

About