Information-theoretic neuro-correlates boost evolution of cognitive systems

Genetic Algorithms (GA) are a powerful set of tools for search and optimization that mimic the process of natural selection, and have been used successfully in a wide variety of problems, including evolving neural networks to solve cognitive tasks. Despite their success, GAs sometimes fail to locate the highest peaks of the fitness landscape, in particular if the landscape is rugged and contains multiple peaks. Reaching distant and higher peaks is difficult because valleys need to be crossed, in a process that (at least temporarily) runs against the fitness maximization objective. Here we propose and test a number of information-theoretic (as well as network-based) measures that can be used in conjunction with a fitness maximization objective (so-called ``neuro-correlates") to evolve neural controllers for two widely different tasks: a behavioral task that requires information integration, and a cognitive task that requires memory and logic. We find that judiciously chosen neuro-correlates can significantly aid GAs to find the highest peaks.

[1]  William J. McGill.  Multivariate information transmission , 1954, Trans. IRE Prof. Group Inf. Theory.

[2]  M. Zlotowski,et al.  Behavioral variability of process and reactive schizophrenics in a binary guessing task. , 1963, Journal of abnormal and social psychology.

[3]  Vladimir Vapnik,et al.  Chervonenkis: On the uniform convergence of relative frequencies of events to their probabilities , 1971 .

[4]  W. A. Wagenaar.  Generation of random sequences by human subjects: A critical survey of literature. , 1972 .

[5]  K. Dejong,et al.  An analysis of the behavior of a class of genetic adaptive systems , 1975 .

[6]  Anas N. Al-Rabadi,et al.  A comparison of modified reconstructability analysis and Ashenhurst‐Curtis decomposition of Boolean functions , 2004 .

[7]  Terry A. Welch,et al.  A Technique for High-Performance Data Compression , 1984, Computer.

[8]  Rodney A. Brooks,et al.  A Robust Layered Control Syste For A Mobile Robot , 2022 .

[9]  G. Edelman,et al.  A measure for brain complexity: relating functional segregation and integration in the nervous system. , 1994, Proceedings of the National Academy of Sciences of the United States of America.

[10]  Peter Norvig,et al.  Artificial Intelligence: A Modern Approach , 1995 .

[11]  P. Brugger,et al.  Random number generation in dementia of the Alzheimer type: A test of frontal executive functions , 1996, Neuropsychologia.

[12]  Pattie Maes,et al.  Toward the Evolution of Dynamical Neural Networks for Minimally Cognitive Behavior , 1996 .

[13]  Zbigniew Michalewicz,et al.  Genetic Algorithms + Data Structures = Evolution Programs , 1996, Springer Berlin Heidelberg.

[14]  A Baddeley,et al.  Random Generation and the Executive Control of Working Memory , 1998, The Quarterly journal of experimental psychology. A, Human experimental psychology.

[15]  X. Yao.  Evolving Artificial Neural Networks , 1999 .

[16]  Richard A. Watson,et al.  Reducing Local Optima in Single-Objective Problems by Multi-objectivization , 2001, EMO.

[17]  Ay Nihat,et al.  Information Geometry on Complexity and Stochastic Interaction , 2001 .

[18]  N. Rinehart,et al.  Brief Report: Random Number Generation in Autism , 2002, Journal of autism and developmental disorders.

[19]  A. U.S.,et al.  Predictability , Complexity , and Learning , 2002 .

[20]  Risto Miikkulainen,et al.  Evolving Neural Networks through Augmenting Topologies , 2002, Evolutionary Computation.

[21]  Randall D. Beer,et al.  The Dynamics of Active Categorical Perception in an Evolved Model Agent , 2003, Adapt. Behav..

[22]  Robert T. Pennock,et al.  The evolutionary origin of complex features , 2003, Nature.

[23]  Peter Norvig,et al.  Artificial intelligence - a modern approach, 2nd Edition , 2003, Prentice Hall series in artificial intelligence.

[24]  Michael J. Berry,et al.  Network information and connected correlations. , 2003, Physical review letters.

[25]  Raul Rodriguez-Esteban,et al.  Global optimization of cerebral cortex layout. , 2004, Proceedings of the National Academy of Sciences of the United States of America.

[26]  Eric O. Postma,et al.  Reactive Agents and Perceptual Ambiguity , 2005, Adapt. Behav..

[27]  N. Rinehart,et al.  Pseudo-random number generation in children with high-functioning autism and Asperger’s disorder , 2006, Autism : the international journal of research and practice.

[28]  Yong-Yeol Ahn,et al.  Wiring cost in the organization of a biological neuronal network , 2005, q-bio/0505009.

[29]  M. Jahanshahi,et al.  Random number generation as an index of controlled processing. , 2006, Neuropsychology.

[30]  Olaf Sporns,et al.  Mapping Information Flow in Sensorimotor Networks , 2006, PLoS Comput. Biol..

[31]  Olaf Sporns,et al.  Methods for quantifying the informational structure of sensory and motor data , 2007, Neuroinformatics.

[32]  Giulio Tononi,et al.  Integrated Information in Discrete Dynamical Systems: Motivation and Theoretical Framework , 2008, PLoS Comput. Biol..

[33]  G. Tononi.  Consciousness as Integrated Information: a Provisional Manifesto , 2008, The Biological Bulletin.

[34]  Ralf Der,et al.  Predictive information and explorative behavior of autonomous robots , 2008 .

[35]  Dario Floreano,et al.  Neuroevolution: from architectures to learning , 2008, Evol. Intell..

[36]  Kenneth O. Stanley,et al.  Exploiting Open-Endedness to Solve Problems Through the Search for Novelty , 2008, ALIFE.

[37]  Giulio Tononi,et al.  Qualia: The Geometry of Integrated Information , 2009, PLoS Comput. Biol..

[38]  L. Marstaller.  Measuring Representation , 2010 .

[39]  Stanislas Leibler,et al.  The Value of Information for Populations in Varying Environments , 2010, ArXiv.

[40]  Kenneth O. Stanley,et al.  Indirect Encoding of Neural Networks for Scalable Go , 2010, PPSN.

[41]  Joel Lehman,et al.  Task switching in multirobot learning through indirect encoding , 2011, 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems.

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

[43]  Kenneth O. Stanley,et al.  On the Performance of Indirect Encoding Across the Continuum of Regularity , 2011, IEEE Transactions on Evolutionary Computation.

[44]  Qingfu Zhang,et al.  Multiobjective evolutionary algorithms: A survey of the state of the art , 2011, Swarm Evol. Comput..

[45]  Anil K. Seth,et al.  Practical Measures of Integrated Information for Time-Series Data , 2011, PLoS Comput. Biol..

[46]  Christof Koch,et al.  The Minimal Complexity of Adapting Agents Increases with Fitness , 2012, ALIFE.

[47]  Arend Hintze,et al.  Evolution of an artificial visual cortex for image recognition , 2013, ECAL.

[48]  Keyan Zahedi,et al.  Linear combination of one-step predictive information with an external reward in an episodic policy gradient setting: a critical analysis , 2013, Front. Psychol..

[49]  Arend Hintze,et al.  Predator confusion is sufficient to evolve swarming behaviour , 2012, Journal of The Royal Society Interface.

[50]  Randal S. Olson,et al.  Critical interplay between density-dependent predation and evolution of the selfish herd , 2013, GECCO '13.

[51]  Arend Hintze,et al.  The Evolution of Representation in Simple Cognitive Networks , 2012, Neural Computation.

[52]  Hod Lipson,et al.  The evolutionary origins of modularity , 2012, Proceedings of the Royal Society B: Biological Sciences.

[53]  Arend Hintze,et al.  Evolution of Autonomous Hierarchy Formation and Maintenance , 2014, ALIFE.

[54]  Randal S. Olson,et al.  Exploring Conditions That Select for the Evolution of Cooperative Group Foraging , 2014 .

[55]  D. Schwab,et al.  Quantifying the Role of Population Subdivision in Evolution on Rugged Fitness Landscapes , 2013, PLoS Comput. Biol..

[56]  Jean-Baptiste Mouret,et al.  Evolving neural networks that are both modular and regular: HyperNEAT plus the connection cost technique , 2014, GECCO.

[57]  Arend Hintze,et al.  Evolution of Integrated Causal Structures in Animats Exposed to Environments of Increasing Complexity , 2014, PLoS Comput. Biol..

[58]  Randal S. Olson,et al.  Exploring the evolution of a trade-off between vigilance and foraging in group-living organisms , 2014, Royal Society Open Science.

[59]  Darrell Whitley,et al.  The Island Model Genetic Algorithm: On Separability, Population Size and Convergence , 2015, CIT 2015.

[60]  Jason Yosinski,et al.  Deep neural networks are easily fooled: High confidence predictions for unrecognizable images , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[61]  Arend Hintze,et al.  Computational evolution of decision-making strategies , 2015, CogSci.

[62]  Randal S. Olson,et al.  Evolution of Swarming Behavior Is Shaped by How Predators Attack , 2013, Artificial Life.

[63]  Sabine Fenstermacher,et al.  Genetic Algorithms Data Structures Evolution Programs , 2016 .

[64]  A. Shamsai,et al.  Multi-objective Optimization , 2017, Encyclopedia of Machine Learning and Data Mining.

[65]  Wenhao Yu,et al.  Supplementary material , 2015 .