Cartesian GP in Optimization of Combinational Circuits with Hundreds of Inputs and Thousands of Gates

Vašíček, Zdeněk

doi:10.1007/978-3-319-16501-1_12

Cited by 29 publications

(9 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally in recent work [46] the role of neutral mutations were investigated in relation to the application of CGP to the minimisation of Boolean circuits. In their work they proposed three criteria for preventing neutral mutations ''(1) inactive gates are never modified; (2) it is not possible to connect an active gate (or primary output) to an inactive gate; (3) the gene which encodes the connection of the second input of a single-input gate is never mutated.''.…”

Section: Redundancy In Cartesian Genetic Programmingmentioning

confidence: 99%

Neutral genetic drift: an investigation using Cartesian Genetic Programming

Turner

Miller

2015

Genet Program Evolvable Mach

View full text Add to dashboard Cite

Neutral genetic drift is an evolutionary mechanism which can strongly aid the escape from local optima. This makes neutral genetic drift an increasingly important property of Evolutionary Computational methods as more challenging applications are approached. Cartesian Genetic Programming (CGP) is a Genetic Programming technique which contains explicit, as well as the more common implicit, genetic redundancy. As explicit genetic redundancy is easily identified and manipulated it represents a useful tool for investigating neutral genetic drift. The contributions of this paper are as follows. Firstly the paper presents a substantial evaluation of the role and benefits of neutral genetic drift in CGP. Here it is shown that the benefits of explicit genetic redundancy are additive to the benefits of implicit genetic redundancy. This is significant as it indicates that that levels of implicit genetic redundancy present in other Evolutionary Computational methods may be insufficient to fully utilise neutral genetic drift. It is also shown than the identification and manipulation of explicit genetic redundancy is far easier than for implicit genetic redundancy. This is significant as it makes the investigations here possible and leads to new possibilities for allowing more effective use of neutral genetic drift. This is the case not only for CGP, but many other Evolutionary Computational methods which contain explicit genetic redundancy. Finally, it is also shown that neutral genetic drift has additional benefits other than aiding the escape from local optima.

show abstract

Section: Redundancy In Cartesian Genetic Programmingmentioning

confidence: 99%

Neutral genetic drift: an investigation using Cartesian Genetic Programming

Turner

Miller

2015

Genet Program Evolvable Mach

View full text Add to dashboard Cite

show abstract

“…The literature shows that, for a fixed number of generated and evaluated candidate solutions, CGP-based circuit optimization (i.e. when circuits are not evolved from scratch) with a smaller value of λ usually leads to better fitness values than CGP using larger values of λ [41].…”

Section: Cgp Parametersmentioning

confidence: 99%

Adaptive verifiability-driven strategy for evolutionary approximation of arithmetic circuits

Češka

Matyas

Mrázek

et al. 2020

Applied Soft Computing

Self Cite

View full text Add to dashboard Cite

“…In its original form, CGP [19] has been deployed to various applications, including the evolution of robotic controllers [10], digital filters [18], computational art [1] and large scale digital circuits [36]. The idea to use the CGP-encoding to represent neural networks goes back to works of Turner and Miller [35] and Khan et al [16], who coined the term CGPANN.…”

Section: Cartesian Genetic Programmingmentioning

confidence: 99%

Neural network architecture search with differentiable cartesian genetic programming for regression

Märtens

Izzo

2019

Proceedings of the Genetic and Evolutionary Computation Conference Companion

View full text Add to dashboard Cite

The ability to design complex neural network architectures which enable effective training by stochastic gradient descent has been the key for many achievements in the field of deep learning. However, developing such architectures remains a challenging and resourceintensive process full of trial-and-error iterations. All in all, the relation between the network topology and its ability to model the data remains poorly understood. We propose to encode neural networks with a differentiable variant of Cartesian Genetic Programming (dCGPANN) and present a memetic algorithm for architecture design: local searches with gradient descent learn the network parameters while evolutionary operators act on the dCGPANN genes shaping the network architecture towards faster learning. Studying a particular instance of such a learning scheme, we are able to improve the starting feed forward topology by learning how to rewire and prune links, adapt activation functions and introduce skip connections for chosen regression tasks. The evolved network architectures require less space for network parameters and reach, given the same amount of time, a significantly lower error on average. KEYWORDSdesigning neural network architectures, evolution, genetic programming, artificial neural networks

show abstract

Cartesian GP in Optimization of Combinational Circuits with Hundreds of Inputs and Thousands of Gates

Cited by 29 publications

References 9 publications

Neutral genetic drift: an investigation using Cartesian Genetic Programming

Neutral genetic drift: an investigation using Cartesian Genetic Programming

Adaptive verifiability-driven strategy for evolutionary approximation of arithmetic circuits

Neural network architecture search with differentiable cartesian genetic programming for regression

Contact Info

Product

Resources

About