On Dynamical Genetic Programming: Random Boolean Networks in Learning Classifier Systems

Bull, Larry; Preen, Richard J.

doi:10.1007/978-3-642-01181-8_4

Cited by 15 publications

(8 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this sense, Boolean functions are individually more expressive than weighted sigmoids. This suggests that Boolean networks might have advantages for certain computational tasks; the few examples where they have been applied to computational tasks tend to support this notion [56,22,14].…”

Section: Biochemical Interactionsmentioning

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

Section: Biochemical Interactionsmentioning

confidence: 99%

Biochemical connectionism

et al. 2013

View full text Add to dashboard Cite

show abstract

“…During the evolution of nervous systems, we do not know whether the physiology of neurons and the phenomena that are exhibited by neurons were selected for because they are well suited to their role as components of evolvable, adaptable information processing systems, or whether their evolution was highly constrained by other factors. If we assume the former, we should consider systematically evaluating models which incorporate one or more of the phenomena exhibited by neurons for their potential use in evolutionary computing schemes (as has been done in [38,39]). The work in this paper is one such model.…”

Section: G Parallels With Neural Information Processingmentioning

confidence: 99%

Time-dependent wave selection for information processing in excitable media

et al. 2012

View full text Add to dashboard Cite

We demonstrate an improved technique for implementing logic circuits in light-sensitive chemical excitable media. The technique makes use of the constant-speed propagation of waves along defined channels in an excitable medium based on the Belousov-Zhabotinsky reaction, along with the mutual annihilation of colliding waves. What distinguishes this work from previous work in this area is that regions where channels meet at a junction can periodically alternate between permitting the propagation of waves and blocking them. These valve-like areas are used to select waves based on the length of time that it takes waves to propagate from one valve to another. In an experimental implementation, the channels which make up the circuit layout are projected by a digital projector connected to a computer. Excitable channels are projected as dark areas, unexcitable regions as light areas. Valves alternate between dark and light: every valve has the same period and phase, with a 50% duty cycle. This scheme can be used to make logic gates based on combinations of OR and AND-NOT operations, with few geometrical constraints. Because there are few geometrical constraints, compact circuits can be implemented. Experimental results from an implementation of a 4-bit input, 2-bit output integer square root circuit are given. This is the most complex logic circuit that has been implemented in BZ excitable media to date.

show abstract

“…Teuscher investigated the non-linear dynamics of A-types [29, ch 5], [30]. Recently, Bull [3], and Bull and Preene [4] investigated the evolution of Atype machines, and they considered this in the context of discrete dynamical systems.…”

Section: Historical Background and Previous Workmentioning

confidence: 99%

“…This started with Wilson [32] and others have also investigated this task, for example Koza [14, ch 7], Butz [5, ch 3]. In particular, Bull and Preene [4] used simulated evolution to design clampable A-types that represent clamped n-multiplexers Although n-multiplexer is more complex than n-identity, it is another class of problem that scales easily.…”

Section: Searching For Clamped N-multiplexermentioning

confidence: 99%

Evolving A-type artificial neural networks

Orr

Martin

2011

Evol. Intel.

View full text Add to dashboard Cite

We investigate Turing's notion of an A-type artificial neural network. We study a refinement of Turing's original idea, motivated by work of Teuscher, Bull, Preen and Copeland. Our A-types can process binary data by accepting and outputting sequences of binary vectors; hence we can associate a function to an A-type, and we say the A-type represents the function. There are two modes of data processing: clamped and sequential. We describe an evolutionary algorithm, involving graph-theoretic manipulations of A-types, which searches for A-types representing a given function. The algorithm uses both mutation and crossover operators. We implemented the algorithm and applied it to three benchmark tasks. We found that the algorithm performed much better than a random search. For two out of the three tasks, the algorithm with crossover performed better than a mutation-only version.

show abstract

On Dynamical Genetic Programming: Random Boolean Networks in Learning Classifier Systems

Cited by 15 publications

References 32 publications

Biochemical connectionism

Biochemical connectionism

Time-dependent wave selection for information processing in excitable media

Evolving A-type artificial neural networks

Contact Info

Product

Resources

About