A comparison of genetic regulatory network dynamics and encoding

Disset, Jean; Wilson, Dennis G.; Cussat‐Blanc, Sylvain; Sanchez, Stéphane; Luga, Hervé; Duthen, Yves

doi:10.1145/3071178.3071322

Cited by 3 publications

(6 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…however, a rigorous comparison of models has yet to be performed. Recently, an initial study has been conducted in order to compare various encodings and dynamics [41]. Without doubt, the community would benefit from standardized of proteins that codes for the dynamic interaction between them.…”

Section: Resultsmentioning

confidence: 99%

Artificial Gene Regulatory Networks—A Review

2019

Self Cite

View full text Add to dashboard Cite

In nature, gene regulatory networks are a key mediator between the information stored in the DNA of living organisms (their genotype) and the structural and behavioral expression this finds in their bodies, surviving in the world (their phenotype). They integrate environmental signals, steer development, buffer stochasticity, and allow evolution to proceed. In engineering, modeling and implementations of artificial gene regulatory networks have been an expanding field of research and development over the past few decades. This review discusses the concept of gene regulation, describes the current state of the art in gene regulatory networks, including modeling and simulation, and reviews their use in artificial evolutionary settings. We provide evidence for the benefits of this concept in natural and the engineering domains.

show abstract

Section: Resultsmentioning

confidence: 99%

Artificial Gene Regulatory Networks—A Review

2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…We will first present the classic computation of the GRN dynamics, using equations found to be optimal in [Disset et al, 2017] on a number of problems. Following this overview, we will present the conversion of these equations into a set of differentiable matrix operations.…”

Section: Methodsmentioning

confidence: 99%

“…It is important to note that the softmax layer is applied before saving the state of the layer; the regulatory protein concentration which affects the next timestep is already normalized. Normalization has been shown to be an important part of artificial GRN evolution and use [Disset et al, 2017], however it may confound deep neural models not accustomed to having a softmax in the interior of the model. In Figure 2, a GRN layer with no normalization is considered.…”

Section: Grn Layermentioning

confidence: 99%

“…Artificial Gene Regulatory Networks (GRNs) have varied in implementation since their conception, with initial boolean network representations that directly encode connections giving way to proteins that interpolate their connection using exponential or other functions. Following inspiration from biology, these models have been optimized using genetic algorithms, with advances in GRN representation often involving improvements to the evolvability of the representation [Kuo et al, 2004], [Cussat-Blanc et al, 2015], [Disset et al, 2017].…”

Section: Introductionmentioning

confidence: 99%

“…Finding similar use to their biological inspiration, GRNs have controlled the design and development of multi-cellular creatures [Cussat-Blanc et al, 2008] and of artificial neural networks (ANNs) [Wróbel and Abdelmotaleb, 2012]. Evolution and dynamics were recently improved in [Cussat-Blanc et al, 2015, Disset et al, 2017. Artificial GRNs have also been used to investigate a number of questions in the context of evolution.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Evolving Differentiable Gene Regulatory Networks

Wilson¹,

Harrington²,

Cussat‐Blanc³

et al. 2018

Preprint

Self Cite

View full text Add to dashboard Cite

Over the past twenty years, artificial Gene Regulatory Networks (GRNs) have shown their capacity to solve real-world problems in various domains such as agent control, signal processing and artificial life experiments. They have also benefited from new evolutionary approaches and improvements to dynamic which have increased their optimization efficiency. In this paper, we present an additional step toward their usability in machine learning applications. We detail an GPUbased implementation of differentiable GRNs, allowing for local optimization of GRN architectures with stochastic gradient descent (SGD). Using a standard machine learning dataset, we evaluate the ways in which evolution and SGD can be combined to further GRN optimization. We compare these approaches with neural network models trained by SGD and with support vector machines.

show abstract

A geometric encoding for neural network evolution

Templier

Rachelson

Wilson

2021

Proceedings of the Genetic and Evolutionary Computation Conference

View full text Add to dashboard Cite

A major limitation to the optimization of artificial neural networks (ANN) with evolutionary methods lies in the high dimensionality of the search space, the number of weights growing quadratically with the size of the network. This leads to expensive training costs, especially in evolution strategies which rely on matrices whose sizes grow with the number of genes. We introduce a geometric encoding for neural network evolution (GENE) as a representation of ANN parameters in a smaller space that scales linearly with the number of neurons, allowing for efficient parameter search. Each neuron of the network is encoded as a point in a latent space and the weight of a connection between two neurons is computed as the distance between them. The coordinates of all neurons are then optimized with evolution strategies in a reduced search space while not limiting network fitness and possibly improving search.

show abstract

A comparison of genetic regulatory network dynamics and encoding

Cited by 3 publications

References 9 publications

Artificial Gene Regulatory Networks—A Review

Artificial Gene Regulatory Networks—A Review

Evolving Differentiable Gene Regulatory Networks

A geometric encoding for neural network evolution

Contact Info

Product

Resources

About