An Application of Category-Theoretic Design Methods to the Control of a Simulated Robot

The use of neural network architectures has historically presented a challenge to engineers. Problem domains could be "learned", but the acquired knowledge could be extracted only under limited circumstances. Healy and Caudell's application of category theory has been shown to improve both architecture design and performance. This paper reports on the application of category theory to the design of a simulated robot control system, where the neural network controller is constructed based upon a desired conceptual ontology. Three experiments then explore the implications of this approach on the prediction and improvement of robot performance.

[1]  Yunhai Xiao,et al.  From categorical semantics to neural network design , 2003, Proceedings of the International Joint Conference on Neural Networks, 2003..

[2]  Michael J. Healy.  A Topological Semantics for Rule Extraction with Neural Networks , 1999, Connect. Sci..

[3]  M. J. Healy,et al.  Modification of the ART-1 architecture based on category theoretic design principles , 2005, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..

[4]  Benjamin C. Peirce,et al.  Basic Category Theory for Computer Scientists , 1991 .

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

[6]  Thomas P. Caudell,et al.  Ontologies and Worlds in Category Theory: Implications for Neural Systems , 2006 .

[7]  B. Achiriloaie,et al.  VI REFERENCES , 1961 .

[8]  Yunhai Xiao,et al.  eLoom: a specification, simulation and visualization engine for modeling arbitrary hierarchical neural architectures , 2003, Proceedings of the International Joint Conference on Neural Networks, 2003..

[9]  Krysia Broda,et al.  Neural-symbolic learning systems - foundations and applications , 2012, Perspectives in neural computing.

[10]  LiMin Fu,et al.  Rule Generation from Neural Networks , 1994, IEEE Trans. Syst. Man Cybern. Syst..

[11]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[12]  Jude W. Shavlik,et al.  Extracting Refined Rules from Knowledge-Based Neural Networks , 1993, Machine Learning.

[13]  Brian Scassellati,et al.  Humanoid Robots: A New Kind of Tool , 2000, IEEE Intell. Syst..

[14]  E. Michael Azoff,et al.  Neural Network Time Series: Forecasting of Financial Markets , 1994 .

[15]  S. Maclane,et al.  General theory of natural equivalences , 1945 .

[16]  Ron Sun,et al.  Robust Reasoning: Integrating Rule-Based and Similarity-Based Reasoning , 1995, Artif. Intell..