Evolving Spiking Neural Networks in the GReaNs (Gene Regulatory evolving artificial Networks) Plaftorm
نویسندگان
چکیده
GReaNs (which stands for Genetic Regulatory evolving artificial Networks) is an artificial life software platform that has previously been used for modeling of evolution of gene regulatory networks able to process signals, control animats and direct multicellular development in two and three dimensions. The structure of the network in GReaNs is encoded in a linear genome, without imposing any restrictions on the size of the genome or the size of the network. Each node in the regulatory network in GReaNs has been considered thus far to be an artificial analog of a biological transcriptional unit. However, they could equally well be seen as artificial neurons. In this extended abstract we present an extension to the GReaNs platform in which the linear genome encodes a spiking neural network which consists of leaky integrate and fire neurons with a fixed threshold, or adaptive-exponential integrate and fire neurons. As a proof-of-principle, we report the evolution of spiking networks that match a desired spiking pattern. Keywords-gene regulatory networks; spiking neural networks; leaky integrate and fire neurons; adaptive-exponential neurons; genetic algorithm
منابع مشابه
Evolving Networks Processing Signals with a Mixed Paradigm, Inspired by Gene Regulatory Networks and Spiking Neurons
In this paper we extend our artificial life platorm, called GReaNs (for Genetic Regulatory evolving artificial Networks) to allow evolution of spiking neural networks performign simple computational tasks. GReaNs has been previously used to model evolution of gene regulatory networks for processing signals, and also for controling the behaviour of unicallular animats and the devlopment of multi...
متن کاملEvolving spiking neural networks for temporal pattern recognition in the presence of noise
Nervous systems of biological organisms use temporal patterns of spikes to encode sensory input, but the mechanisms that underlie the recognition of such patterns are unclear. In the present work, we explore how networks of spiking neurons can be evolved to recognize temporal input patterns without being able to adjust signal conduction delays. We evolve the networks with GReaNs, an artificial ...
متن کاملEvolution of spiking neural networks for temporal pattern recognition and animat control
Evolution of Spiking Neural Networks for Temporal Pattern Recognition and Animat Control. I extended an artificial life platform called GReaNs (the name stands for Gene Regulatory evolving artificial Networks) to explore the evolutionary abilities of biologically inspired Spiking Neural Network (SNN) model. The encoding of SNNs in GReaNs was inspired by the encoding of gene regulatory networks....
متن کاملAdaptive Neural Networks, Gene Networks, and Evolutionary Systems – Real and Artificial Evolving Intelligence
The paper presents an integrated approach to building evolving artificial intelligent systems in terms of evolving connectionist systems (ECOS) that capture principles from neural networks, gene interaction networks and evolutionary systems. The ECOS can be used to solve complex problems from computational biology that is illustrated on a simplified gene regulatory network modeling problem. The...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2012