S-Learning: A Biomimetic Algorithm for Learning, Memory, and Control in Robots

S-learning is a sequence-based learning algorithm patterned on human motor behavior. Discrete-time and quantized sensory information is amassed in real-time to form a dynamic model of the system being controlled and its environment. No explicit model is provided a priori, nor any hint about what the structure of the model might be. As the core of a Brain-Emulating Cognition and Control Architecture (BECCA), S-Learning provides a mechanism for human-inspired learning, memory, and control in machines. In a simulation of a point-to-point reaching task, S-Learning demonstrates several attributes of human motor behavior, including learning through exploration and task transfer.

[1]  R. Granger,et al.  Derivation and Analysis of Basic Computational Operations of Thalamocortical Circuits , 2004, Journal of Cognitive Neuroscience.

[2]  F. Varela,et al.  A quantitative assessment of the dependency of the visual temporal frame upon the cortical rhythm. , 1988, Journal de physiologie.

[3]  N. Hogan,et al.  Submovements grow larger, fewer, and more blended during stroke recovery. , 2003, Motor control.

[4]  C. Koch,et al.  Is perception discrete or continuous? , 2003, Trends in Cognitive Sciences.

[5]  N. Hogan,et al.  Quantization of continuous arm movements in humans with brain injury. , 1999, Proceedings of the National Academy of Sciences of the United States of America.

[6]  W. James,et al.  The Principles of Psychology. , 1983 .

[7]  J. Wessberg,et al.  Single motor unit activity in relation to pulsatile motor output in human finger movements , 1999, The Journal of physiology.

[8]  William B. Levy,et al.  The formation of neural codes in the hippocampus: trace conditioning as a prototypical paradigm for studying the random recoding hypothesis , 2005, Biological Cybernetics.

[9]  Lorien Y. Pratt,et al.  A Survey of Connectionist Network Reuse Through Transfer , 1998, Learning to Learn.

[10]  T. Milner,et al.  A model for the generation of movements requiring endpoint precision , 1992, Neuroscience.

[11]  A. Schnitzler,et al.  The neural basis of intermittent motor control in humans , 2002, Proceedings of the National Academy of Sciences of the United States of America.

[12]  C. Hofsten,et al.  Structuring of early reaching movements: a longitudinal study. , 1991 .

[13]  Jürgen Schmidhuber,et al.  Reinforcement Learning with Self-Modifying Policies , 1998, Learning to Learn.

[14]  J. Wessberg,et al.  Organization of motor output in slow finger movements in man. , 1993, The Journal of physiology.

[15]  Robert Sessions Woodworth,et al.  THE ACCURACY OF VOLUNTARY MOVEMENT , 1899 .

[16]  A. Felch,et al.  Engines of the Brain: The Computational "Instruction Set" of Perception and Cognition , 2004, AAAI Technical Report.

[17]  Sebastian Thrun,et al.  Learning to Learn , 1998, Springer US.

[18]  D. Shepard.  A two-dimensional interpolation function for irregularly-spaced data , 1968, ACM National Conference.

[19]  D. Purves,et al.  The wagon wheel illusion in movies and reality. , 1996, Proceedings of the National Academy of Sciences of the United States of America.

[20]  Joshua B. Tenenbaum,et al.  Bayesian Modeling of Human Concept Learning , 1998, NIPS.

[21]  Peter Sollich,et al.  Advances in neural information processing systems 11 , 1999 .

[22]  Lorien Y. Pratt,et al.  A Survey of Transfer Between Connectionist Networks , 1996, Connect. Sci..

[23]  Michael I. Jordan,et al.  Advances in Neural Information Processing Systems 30 , 1995 .

[24]  C. Marsden,et al.  Human anticipatory eye movements may reflect rhythmic central nervous activity , 1999, Neuroscience.

[25]  Jonathan Baxter,et al.  Theoretical Models of Learning to Learn , 1998, Learning to Learn.

[26]  Nathan Intrator,et al.  Making a Low-Dimensional Representation Suitable for Diverse Tasks , 1998, Learning to Learn.

[27]  Wolf Singer,et al.  Neuronal Synchrony: A Versatile Code for the Definition of Relations? , 1999, Neuron.