Markov Brains: A technical introduction

作     者：Hintze, Arend Edlund, Jeffrey A. Olson, Randal S. Knoester, David B. Schossau, Jory Albantakis, Larissa Tehrani-Saleh, Ali Kvam, Peter Sheneman, Leigh Goldsby, Heather Bohm, Clifford Adami, Christoph 

作者机构：Department of Computer Science & Engineering Michigan State University Department of Integrative Biology Michigan State University BEACON Center for the Study of Evolution in Action Michigan State University Computation & Neural Systems California Institute of Technology Institute for Biomedical Informatics University of Pennsylvania Department of Psychiatry University of Wisconsin Department of Psychological & Brain Sciences Indiana University Department of Microbiology & Molecular Genetics Michigan State University Department of Physics & Astronomy Michigan State University 

出 版 物：《arXiv》 (arXiv)

年 卷 期：2017年

核心收录：

主　　题：Optimization 

摘      要：Markov Brains are a class of evolvable artificial neural networks (ANN). They differ from conventional ANNs in many aspects, but the key difference is that instead of a layered architecture, with each node performing the same function, Markov Brains are networks built from individual computational components. These computational components interact with each other, receive inputs from sensors, and control motor outputs. The function of the computational components, their connections to each other, as well as connections to sensors and motors are all subject to evolutionary optimization. Here we describe in detail how a Markov Brain works, what techniques can be used to study them, and how they can be evolved. Copyright © 2017, The Authors. All rights reserved.