Investigation of rat exploratory behavior via evolving artificial neural networks

BACKGROUND Neuroevolution comprises the use of evolutionary computation to define the architecture and/or to train artificial neural networks (ANNs). This strategy has been employed to investigate the behavior of rats in the elevated plus-maze, which is a widely used tool for studying anxiety in mice and rats. NEW METHOD Here we propose a neuroevolutionary model, in which both the weights and the architecture of artificial neural networks (our virtual rats) are evolved by a genetic algorithm. COMPARISON WITH EXISTING METHOD(S) This model is an improvement of a previous model that involves the evolution of just the weights of the ANN by the genetic algorithm. In order to compare both models, we analyzed traditional measures of anxiety behavior, like the time spent and the number of entries in both open and closed arms of the maze. RESULTS When compared to real rat data, our findings suggest that the results from the model introduced here are statistically better than those from other models in the literature. CONCLUSIONS In this way, the neuroevolution of architecture is clearly important for the development of the virtual rats. Moreover, this technique allowed the comprehension of the importance of different sensory units and different number of hidden neurons (performing as memory) in the ANNs (virtual rats).

[1]  Renato Tinós,et al.  An Evolving Artificial Neural Network for the Investigation of Rat Exploratory Behavior , 2014, 2014 Brazilian Conference on Intelligent Systems.

[2]  S. Morato,et al.  Vibrissal sense is not the main sensory modality in rat exploratory behavior in the elevated plus-maze , 2001, Behavioural Brain Research.

[3]  Xin Yao,et al.  Evolving artificial neural networks , 1999, Proc. IEEE.

[4]  A. Costa,et al.  A computational model for exploratory activity of rats with different anxiety levels in elevated plus-maze , 2014, Journal of Neuroscience Methods.

[5]  David A. Miranda.  Modelado del Comportamiento de Ratas en Laberinto en Cruz Elevado Basado en Redes Neuronales Artificiales , 2009 .

[6]  D. M. Hutton,et al.  Advances in the Evolutionary Synthesis of Intelligent Agents , 2002 .

[7]  B. C. Deer,et al.  An exploration of genetic algorithms for the selection of connection weights in dynamical neural networks , 1991, Proceedings of the IEEE 1991 National Aerospace and Electronics Conference NAECON 1991.

[8]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[9]  Renato Tinós,et al.  Use of Evolutionary Robots as an Auxiliary Tool for Developing Behavioral Models of Rats in an Elevated Plus-Maze , 2010, 2010 Eleventh Brazilian Symposium on Neural Networks.

[10]  Antônio C. Roque-da-Silva,et al.  Anxiety-like behavior in rats: a computational model , 2000, Neural Networks.

[11]  B. Webb,et al.  Can robots make good models of biological behaviour? , 2001, Behavioral and Brain Sciences.

[12]  H. de Garis.  GenNets: genetically programmed neural nets-using the genetic algorithm to train neural nets whose inputs and/or outputs vary in time , 1991, [Proceedings] 1991 IEEE International Joint Conference on Neural Networks.

[13]  James A. Reggia,et al.  The Automated Design of Artificial Neural Networks Using Evolutionary Computation , 2008 .

[14]  Andrea de Giorgio,et al.  Learning programs is better than learning dynamics: A programmable neural network hierarchical architecture in a multi-task scenario , 2016, Adapt. Behav..

[15]  E. Ruppin.  Evolutionary autonomous agents: A neuroscience perspective , 2002, Nature Reviews Neuroscience.

[16]  Renato Tinós,et al.  Using explicit averaging fitness for studying the behaviour of rats in a maze , 2013, ECAL.

[17]  Dorothea Heiss-Czedik,et al.  An Introduction to Genetic Algorithms. , 1997, Artificial Life.

[18]  S. File,et al.  Validation of open : closed arm entries in an elevated plus-maze as a measure of anxiety in the rat , 1985, Journal of Neuroscience Methods.

[19]  K. Montgomery,et al.  The relation between fear induced by novel stimulation and exploratory behavior. , 1955, Journal of comparative and physiological psychology.

[20]  Jeffrey L. Krichmar,et al.  Evolutionary robotics: The biology, intelligence, and technology of self-organizing machines , 2001, Complex..

[21]  K. Montgomery,et al.  The relation between fear induced by novel stimulation and exploratory drive. , 1955 .

[22]  Joanna Marie Giddings.  MODELING THE BEHAVIOR OF RATS IN AN ELEVATED PLUS-MAZE , 2002 .

[23]  Randall D. Beer,et al.  Evolving Dynamical Neural Networks for Adaptive Behavior , 1992, Adapt. Behav..

[24]  Arend Hintze,et al.  Integrated Information Increases with Fitness in the Evolution of Animats , 2011, PLoS Comput. Biol..

[25]  James A. Reggia,et al.  Evolving processing speed asymmetries and hemispheric interactions in a neural network model , 2005, Neurocomputing.

[26]  Juliana B. Tejada,et al.  Mathematical methods to model rodent behavior in the elevated plus-maze , 2013, Journal of Neuroscience Methods.

[27]  Vasant Honavar,et al.  Evolving Neuro-Controllers and Sensors for Artificial Agents , 2001 .

[28]  S. Hogg.  A review of the validity and variability of the Elevated Plus-Maze as an animal model of anxiety , 1996, Pharmacology Biochemistry and Behavior.

[29]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[30]  Antônio C. Roque-da-Silva,et al.  A Model Based on Genetic Algorithm for Investigation of the Behavior of Rats in the Elevated Plus-Maze , 2012, IDEAL.

[31]  Michael L. Littman,et al.  Reinforcement learning improves behaviour from evaluative feedback , 2015, Nature.

[32]  Jeffrey L. Elman,et al.  Finding Structure in Time , 1990, Cogn. Sci..

[33]  James A. Reggia,et al.  Cost minimization during simulated evolution of paired neural networks leads to asymmetries and specialization , 2003, Cognitive Systems Research.

[34]  David Brown,et al.  Pharmacodynamic Modeling of Anti-Cancer Activity of Tetraiodothyroacetic Acid in a Perfused Cell Culture System , 2011, PLoS Comput. Biol..

[35]  S. Morato,et al.  Effect of different illumination levels on rat behavior in the elevated plus-maze , 2005, Physiology & Behavior.

[36]  Lalit M. Patnaik,et al.  Learning neural network weights using genetic algorithms-improving performance by search-space reduction , 1991, [Proceedings] 1991 IEEE International Joint Conference on Neural Networks.

[37]  Silvio Morato,et al.  Characterization of the rat exploratory behavior in the elevated plus-maze with Markov chains , 2010, Journal of Neuroscience Methods.