Evolvability and Speed of Evolutionary Algorithms in Light of Recent Developments in Biology

Hu, Ting; Banzhaf, Wolfgang

doi:10.1155/2010/568375

Cited by 41 publications

(39 citation statements)

References 205 publications

(250 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Because evolutionary computation (EC) as a whole struggles with evolvability (Wagner and Altenberg, 1996;Reisinger et al, 2005;Hu and Banzhaf, 2010), the subfield of ER naturally confronts the same issue (Lehman and Stanley, 2011b;Tarapore and Mouret, 2015). A distracting complication when discussing or quantifying evolvability is the lack of consensus on evolvability's definition across biology (Pigliucci, 2008), EC in general (Altenberg, 1994;Reisinger et al, 2005), or ER in particular (Lehman and Stanley, 2011b;Tarapore and Mouret, 2015).…”

Section: Evolvability In Evolutionary Roboticsmentioning

confidence: 99%

On the Critical Role of Divergent Selection in Evolvability

2016

View full text Add to dashboard Cite

An ambitious goal in evolutionary robotics (ER) is to evolve increasingly complex robotic behaviors with minimal human design effort. Reaching this goal requires evolutionary algorithms that can unlock from genetic encodings their latent potential for evolvability. One issue clouding this goal is conceptual confusion about evolvability that often obscures important or desirable aspects of evolvability. The danger from such confusion is that it may establish unrealistic goals for evolvability that prove unproductive in practice. An important issue separate from conceptual confusion is the common misalignment between selection and evolvability in ER. While more expressive encodings can represent higher-level adaptations (e.g. sexual reproduction or developmental systems) that increase long-term evolutionary potential (i.e. evolvability), realizing such potential requires gradients of fitness and evolvability to align. In other words, selection is often a critical factor limiting increasing evolvability. Thus, drawing from a series of recent papers, this article seeks to both (1) clarify and focus the ways in which the term evolvability is used within artificial evolution and (2) argue for the importance of one type of selection, i.e. divergent selection, for enabling evolvability. The main argument is that there is a fundamental connection between divergent selection and evolvability (on both the individual and population level) that does not hold for typical goal-oriented selection. The conclusion is that selection pressure plays a critical role in realizing the potential for evolvability and that divergent selection in particular provides a principled mechanism for encouraging evolvability in artificial evolution.

show abstract

Section: Evolvability In Evolutionary Roboticsmentioning

confidence: 99%

On the Critical Role of Divergent Selection in Evolvability

2016

View full text Add to dashboard Cite

show abstract

“…Hu and Banzhaf in [9] have argued that adopting new knowledge about natural evolution generated in areas such as molecular genetics, cell biology, developmental biology, and evolutionary biology would benefit the field of evolutionary computation. The authors discussed evolvability and methods for accelerating artificial evolution by introducing notions from biology and their potential in designing new algorithms in EC.…”

Section: Evolvabilitymentioning

confidence: 99%

Bayesian Inference to Sustain Evolvability in Genetic Programming

Kattan¹,

Ong

2015

Proceedings in Adaptation, Learning and Optimization

View full text Add to dashboard Cite

Abstract. This paper proposes a new framework, referred to as Recurrent Bayesian Genetic Programming (rbGP), to sustain steady convergence in Genetic Programming (GP) (i.e., to prevent premature convergence) and effectively improves its ability to find superior solutions that generalise well. The term 'Recurrent' is borrowed from the taxonomy of Neural Networks (NN), in which a Recurrent NN (RNN) is a special type of network that uses a feedback loop, usually to account for temporal information embedded in the sequence of data points presented to the network. Unlike RNN, our algorithm's temporal dimension pertains to the sequential nature of the evolutionary process itself, and not to the data sampled from the problem solution space. rbGP introduces an intermediate generation between each subsequent generation in order to collect information about the offspring's fitness distribution of each parent. Placing the collected information into a Bayesian model, rbGP predicts the probability of any individual to produce offspring fitter than its parent. This predicted probability (calculated by the Bayesian model) is used by the tournament selection instead of the original fitness value. Empirical evidence, from 13 problems, against canonical GP, demonstrates that rbGP preserves generalisation in most cases.

show abstract

“…mutation, recombination) are available. However, in practice it is beneficial to use a representation that is evolvable, so that when it is mutated or recombined there is a tendency for the evolutionary algorithm to explore fitter variants-or, at least, variants that are not significantly worse on average [62,42]. In computer science in general, there are many examples of representations that are not evolvable, i.e.…”

Section: Evolvabilitymentioning

confidence: 99%

Biochemical connectionism

et al. 2013

View full text Add to dashboard Cite

In this paper, we discuss computational architectures that are motivated by connectionist patterns that occur in biochemical networks, and speculate about how this biochemical approach to connectionism might complement conventional neural approaches. In particular, we focus on three features of biochemical networks that make them distinct from neural networks: their diverse, complex nodal processes, their emergent organisation, and the dynamical behaviours that result from higher-order, self-modifying processes. We also consider the growing use of evolutionary algorithms in the design of connectionist systems, noting how this enables us to explore a wider range of connectionist architectures, and how the close relationship between biochemical networks and biological evolution can guide us in this endeavour.

show abstract

Evolvability and Speed of Evolutionary Algorithms in Light of Recent Developments in Biology

Cited by 41 publications

References 205 publications

On the Critical Role of Divergent Selection in Evolvability

On the Critical Role of Divergent Selection in Evolvability

Bayesian Inference to Sustain Evolvability in Genetic Programming

Biochemical connectionism

Contact Info

Product

Resources

About