Learning a World Model and Planning with a Self-Organizing, Dynamic Neural System

We present a connectionist architecture that can learn a model of the relations between perceptions and actions and use this model for behavior planning. State representations are learned with a growing self-organizing layer which is directly coupled to a perception and a motor layer. Knowledge about possible state transitions is encoded in the lateral connectivity. Motor signals modulate this lateral connectivity and a dynamic field on the layer organizes a planning process. All mechanisms are local and adaptation is based on Hebbian ideas. The model is continuous in the action, perception, and time domain.

[1]  W. Singer,et al.  In search of common foundations for cortical computation , 1997, Behavioral and Brain Sciences.

[2]  Ben J. A. Kröse,et al.  A self-organizing representation of sensor space for mobile robot navigation , 1994, Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS'94).

[3]  Roman Bek,et al.  Discourse on one way in which a quantum-mechanics language on the classical logical base can be built up , 1978, Kybernetika.

[4]  Michael I. Jordan,et al.  Forward Models: Supervised Learning with a Distal Teacher , 1992, Cogn. Sci..

[5]  John N. Tsitsiklis,et al.  Neuro-Dynamic Programming , 1996, Encyclopedia of Machine Learning.

[6]  Rick Grush,et al.  The emulation theory of representation: Motor control, imagery, and perception , 2004, Behavioral and Brain Sciences.

[7]  Geoffrey E. Hinton,et al.  GTM through time , 1997 .

[8]  Bernd Fritzke,et al.  A Growing Neural Gas Network Learns Topologies , 1994, NIPS.

[9]  Jan C. Wiemer,et al.  The Time-Organized Map Algorithm: Extending the Self-Organizing Map to Spatiotemporal Signals , 2003, Neural Computation.

[10]  Andrew G. Barto,et al.  Reinforcement learning , 1998 .

[11]  Teuvo Kohonen,et al.  Self-Organizing Maps , 2010 .

[12]  S. Amari.  Dynamics of pattern formation in lateral-inhibition type neural fields , 1977, Biological Cybernetics.

[13]  Stephen Grossberg,et al.  Fuzzy ARTMAP: A neural network architecture for incremental supervised learning of analog multidimensional maps , 1992, IEEE Trans. Neural Networks.

[14]  S. Hochreiter,et al.  REINFORCEMENT DRIVEN INFORMATION ACQUISITION IN NONDETERMINISTIC ENVIRONMENTS , 1995 .

[15]  Richard S. Sutton,et al.  Introduction to Reinforcement Learning , 1998 .

[16]  Panu Somervuo,et al.  Time topology for the self-organizing map , 1999, IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339).

[17]  Yeuvo Jphonen,et al.  Self-Organizing Maps , 1995 .

[18]  Geoffrey E. Hinton,et al.  Schemata and Sequential Thought Processes in PDP Models , 1986 .

[19]  J. Urgen Schmidhuber,et al.  Adaptive confidence and adaptive curiosity , 1991, Forschungsberichte, TU Munich.

[20]  C. Malsburg.  Self-organization of orientation sensitive cells in the striate cortex , 2004, Kybernetik.

[21]  Paul Bourgine,et al.  Exploration of Multi-State Environments: Local Measures and Back-Propagation of Uncertainty , 1999, Machine Learning.

[22]  G. Hesslow.  Conscious thought as simulation of behaviour and perception , 2002, Trends in Cognitive Sciences.

[23]  Uwe R. Zimmer,et al.  Robust world-modelling and navigation in a real world , 1996, Neurocomputing.