Evolution of Time in Neural Networks: From the Present to the Past, and Forward to the Future

What is time? Since the function of the brain is closely tied in with that of time, investigating the origin of time in the brain can help shed light on this question. In this paper, we propose to use simulated evolution of artificial neural networks to investigate the relationship between time and brain function, and the evolution of time in the brain. A large number of neural network models are based on a feedforward topology (perceptrons, backpropagation networks, radial basis functions, support vector machines, etc.), thus lacking dynamics. In such networks, the order of input presentation is meaningless (i.e., it does not affect the behavior) since the behavior is largely reactive. That is, such neural networks can only operate in the present, having no access to the past or the future. However, biological neural networks are mostly constructed with a recurrent topology, and recurrent (artificial) neural network models are able to exhibit rich temporal dynamics, thus time becomes an essential factor in their operation. In this paper, we will investigate the emergence of recollection and prediction in evolving neural networks. First, we will show how reactive, feedforward networks can evolve a memory-like function (recollection) through utilizing external markers dropped and detected in the environment. Second, we will investigate how recurrent networks with more predictable internal state trajectory can emerge as an eventual winner in evolutionary struggle when competing networks with less predictable trajectory show the same level of behavioral performance. We expect our results to help us better understand the evolutionary origin of recollection and prediction in neuronal networks, and better appreciate the role of time in brain function.

[1]  David L. Wood,et al.  THE ROLE OF PHEROMONES, KAIROMONES, AND ALLOMONES IN THE HOST SELECTION AND COLONIZATION BEHAVIOR OF BARK BEETLES , 1982 .

[2]  Robert Rosen,et al.  Anticipatory systems : philosophical, mathematical, and methodological foundations , 1985 .

[3]  P. Goldman-Rakic,et al.  Preface: Cerebral Cortex Has Come of Age , 1991 .

[4]  Christopher M. Bishop,et al.  Neural networks for pattern recognition , 1995 .

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

[6]  Yoonsuck Choe,et al.  Facilitating neural dynamics for delay compensation and prediction in evolutionary neural networks , 2006, GECCO.

[7]  R. Meech,et al.  Central circuitry in the jellyfish Aglantha digitale IV. Pathways coordinating feeding behaviour , 2003, Journal of Experimental Biology.

[8]  Yoonsuck Choe,et al.  Enhanced Facilitatory Neuronal Dynamics for Delay Compensation , 2007, 2007 International Joint Conference on Neural Networks.

[9]  Steven Churchill,et al.  The vortex , 1999, SIGGRAPH '99.

[10]  Robert Ward,et al.  Cognitive conflict without explicit conflict monitoring in a dynamical agent , 2006, Neural Networks.

[11]  Jeffrey L. Krichmar,et al.  The Neuromodulatory System: A Framework for Survival and Adaptive Behavior in a Challenging World , 2008, Adapt. Behav..

[12]  Yoonsuck Choe,et al.  Delay Compensation Through Facilitating Synapses and STDP: A Neural Basis for Orientation Flash-Lag Effect , 2006, The 2006 IEEE International Joint Conference on Neural Network Proceedings.

[13]  Sanjay Chandrasekharan,et al.  The Origin of Epistemic Structures and Proto-Representations , 2007, Adapt. Behav..

[14]  J. Hildebrand,et al.  Analysis of chemical signals by nervous systems. , 1995, Proceedings of the National Academy of Sciences of the United States of America.

[15]  Yoonsuck Choe,et al.  Neural conduction delay forces the emergence of predictive function in simulated evolution , 2010, BMC Neuroscience.

[16]  Risto Miikkulainen,et al.  Efficient evolution of neural network topologies , 2002, Proceedings of the 2002 Congress on Evolutionary Computation. CEC'02 (Cat. No.02TH8600).

[17]  Risto Miikkulainen,et al.  Contour integration and segmentation with self-organized lateral connections , 2004, Biological Cybernetics.

[18]  Yoonsuck Choe,et al.  Facilitatory neural activity compensating for neural delays as a potential cause of the flash-lag effect , 2005, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..

[19]  Henry Markram,et al.  Network-Related Challenges and Insights from Neuroscience , 2007, BIOWIRE.

[20]  J. Nazuno.  Haykin, Simon. Neural networks: A comprehensive foundation, Prentice Hall, Inc. Segunda Edición, 1999 , 2000 .

[21]  Tao Xiong,et al.  A combined SVM and LDA approach for classification , 2005, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..

[22]  D. J. Felleman,et al.  Distributed hierarchical processing in the primate cerebral cortex. , 1991, Cerebral cortex.

[23]  Yoonsuck Choe,et al.  Facilitating neural dynamics for delay compensation: A road to predictive neural dynamics? , 2009, Neural Networks.

[24]  H. Offret.  Computational Maps in the Visual Cortex , 2006 .

[25]  Lars-Göran Nilsson,et al.  Perspectives on memory research : essays in honor of Uppsala University's 500th anniversary , 1979 .

[26]  Yoonsuck Choe,et al.  Internal state predictability as an evolutionary precursor of self-awareness and agency , 2008, 2008 7th IEEE International Conference on Development and Learning.

[27]  U. Lendahl,et al.  Central nervous system stem cells in the embryo and adult , 1998, Cellular and Molecular Life Sciences CMLS.

[28]  G. J. Blomquist,et al.  Insect pheromones--an overview of biosynthesis and endocrine regulation. , 1999, Insect biochemistry and molecular biology.

[29]  Yoonsuck Choe,et al.  Compensating for Neural Transmission Delay Using Extrapolatory Neural Activation in Evolutionary Neural Networks , 2006 .

[30]  Yoonsuck Choe,et al.  Extrapolative Delay Compensation Through Facilitating Synapses and Its Relation to the Flash-Lag Effect , 2008, IEEE Transactions on Neural Networks.

[31]  Luis Mateus Rocha.  Eigenbehavior and symbols , 1996 .

[32]  Joachim M. Buhmann,et al.  Sensory segmentation with coupled neural oscillators , 1992, Biological Cybernetics.

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

[34]  Yoonsuck Choe,et al.  Evolution of recollection and prediction in neural networks , 2009, 2009 International Joint Conference on Neural Networks.

[35]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[36]  R. Beer.  Dynamical approaches to cognitive science , 2000, Trends in Cognitive Sciences.

[37]  Yoonsuck Choe,et al.  Emergence of Memory-like Behavior in Reactive Agents Using External Markers , 2009, 2009 21st IEEE International Conference on Tools with Artificial Intelligence.

[38]  C.W. Anderson,et al.  Learning to control an inverted pendulum using neural networks , 1989, IEEE Control Systems Magazine.

[39]  Michael R. Conover,et al.  Predator-Prey Dynamics: The Role of Olfaction , 2007 .

[40]  Sanjay Chandrasekharan,et al.  Reactive Agents Learn to Add Epistemic Structures to the World , 2004 .

[41]  J. Elman.  Distributed Representations, Simple Recurrent Networks, And Grammatical Structure , 1991 .

[42]  Tucker R. Balch,et al.  Avoiding the past: a simple but effective strategy for reactive navigation , 1993, [1993] Proceedings IEEE International Conference on Robotics and Automation.

[43]  D. Chalmers.  The conscious mind: in search of a fundamental theory , 1996 .

[44]  J. Hawkins,et al.  On Intelligence , 2004 .

[45]  Risto Miikkulainen,et al.  2-D Pole Balancing with Recurrent Evolutionary Networks , 1998 .

[46]  Alan Carleton,et al.  Sonic hedgehog controls stem cell behavior in the postnatal and adult brain , 2005, Development.

[47]  G Vassart,et al.  Specific repertoire of olfactory receptor genes in the male germ cells of several mammalian species. , 1997, Genomics.