The potential of fuzzy neural networks in the realization of approximate reasoning engines

Fuzzy neurons and fuzzy neural networks (FNN) are constructs of computational intelligence that come with significant learning abilities and inherent transparency (interpretability). Consequently, they exhibit high potential to provide strong mechanisms for building intelligent systems that must operate in rapidly changing environments. However, to fully exploit the potential of FNN structures, efficient parallel-processing implementations are highly desired. In this study, our objective is to investigate this avenue and identify various critical hardware design issues as we propose a versatile neurofuzzy platform with a topology strongly influenced by theories of fuzzy modelling. With a novel hybrid-learning scheme involving structural and parametric optimization, we demonstrate how fuzzy neural networks are well suited in forming the adaptive logic-processing core of this platform, supporting intelligent information processing. The core emulates aspects of human thought, dealing with information at a granular level and using logic-oriented approximate reasoning to solve a problem. It is able to learn and approximate real-world concepts, building a knowledge base that may be interpreted and modified by the user. Drawing upon this knowledge, a high-speed parallel implementation has potential for performing inference of many simultaneous concepts in real-time, realizing cognition as it perceives the current state of its environment.

[1]  Jagath C. Rajapakse,et al.  Neural networks in FPGAs , 2002, Proceedings of the 9th International Conference on Neural Information Processing, 2002. ICONIP '02..

[2]  Constantin V. Negoita,et al.  On Fuzzy Systems , 1978 .

[3]  Donald E. Thomas,et al.  The Verilog® Hardware Description Language , 1990 .

[4]  Edmund M. Clarke,et al.  SAT-based algorithms for logic minimization , 2003, Proceedings 21st International Conference on Computer Design.

[5]  Chong Ho Lee,et al.  Hardware implementation of neural network with expansible and reconfigurable architecture , 2002, Proceedings of the 9th International Conference on Neural Information Processing, 2002. ICONIP '02..

[6]  Witold Pedrycz,et al.  Genetically optimized logic models , 2005, Fuzzy Sets Syst..

[7]  W. Pedrycz,et al.  OR/AND neuron in modeling fuzzy set connectives , 1994, IEEE Trans. Fuzzy Syst..

[8]  Witold Pedrycz,et al.  Heterogeneous fuzzy logic networks: fundamentals and development studies , 2004, IEEE Transactions on Neural Networks.

[9]  Faizal Arya Samman,et al.  Analog MOS circuit design for reconfigurable fuzzy logic controller , 2002, Asia-Pacific Conference on Circuits and Systems.

[10]  Ioannis Andreadis,et al.  Design and implementation of a fuzzy hardware structure for morphological color image processing , 2003, IEEE Trans. Circuits Syst. Video Technol..

[11]  Steven M. Nowick,et al.  Fast heuristic and exact algorithms for two-level hazard-free logic minimization , 1998, IEEE Trans. Comput. Aided Des. Integr. Circuits Syst..

[12]  Jan Hlavicka,et al.  BOOM-a heuristic Boolean minimizer , 2001, IEEE/ACM International Conference on Computer Aided Design. ICCAD 2001. IEEE/ACM Digest of Technical Papers (Cat. No.01CH37281).

[13]  Albert H. Titus,et al.  A new wide range Euclidean distance circuit for neural network hardware implementations , 2003, IEEE Trans. Neural Networks.

[14]  Nadia Nedjah,et al.  FPGA-based hardware architecture for neural networks: binary radix vs. stochastic , 2003, 16th Symposium on Integrated Circuits and Systems Design, 2003. SBCCI 2003. Proceedings..

[15]  Witold Pedrycz,et al.  Evolutionary fuzzy modeling , 2003, IEEE Trans. Fuzzy Syst..

[16]  Frank Vahid,et al.  A codesigned on-chip logic minimizer , 2003, First IEEE/ACM/IFIP International Conference on Hardware/ Software Codesign and Systems Synthesis (IEEE Cat. No.03TH8721).

[17]  Yngvar Berg,et al.  Real-time reconfigurable linear threshold elements implemented in floating-gate CMOS , 2003, IEEE Trans. Neural Networks.

[18]  Kaddour Najim,et al.  Fuzzy neural networks and application to the FBC process , 1996 .

[19]  Shigeo Sato,et al.  Implementation of a new neurochip using stochastic logic , 2003, IEEE Trans. Neural Networks.

[20]  Alessandro De Gloria,et al.  Hardware design of asynchronous fuzzy controllers , 1996, IEEE Trans. Fuzzy Syst..

[21]  Witold Pedrycz,et al.  Fuzzy sets engineering , 1995 .

[22]  Marin Hristov,et al.  Analog implementation of ANN with inherent quadratic nonlinearity of the synapses , 2003, IEEE Trans. Neural Networks.

[23]  James Kennedy,et al.  Particle swarm optimization , 2002, Proceedings of ICNN'95 - International Conference on Neural Networks.

[24]  Alessandro De Gloria,et al.  Fuzzy logic microcontroller , 1997, IEEE Micro.

[25]  Witold Pedrycz,et al.  Fuzzy-set based models of neurons and knowledge-based networks , 1993, IEEE Trans. Fuzzy Syst..

[26]  Mohan M. Trivedi,et al.  A neuro-fuzzy controller for mobile robot navigation and multirobot convoying , 1998, IEEE Trans. Syst. Man Cybern. Part B.

[27]  Dorothea Heiss-Czedik,et al.  An Introduction to Genetic Algorithms. , 1997, Artificial Life.

[28]  R. M. Goodman,et al.  Analog VLSI neural network with digital perturbative learning , 2002 .

[29]  Liliane Peters,et al.  Design and application of an analog fuzzy logic controller , 1996, IEEE Trans. Fuzzy Syst..

[30]  Yutaka Maeda,et al.  FPGA implementation of a pulse density neural network with learning ability using simultaneous perturbation , 2003, IEEE Trans. Neural Networks.

[31]  Rabi N. Mahapatra,et al.  M-trie: an efficient approach to on-chip logic minimization , 2004, IEEE/ACM International Conference on Computer Aided Design, 2004. ICCAD-2004..

[32]  Zoran A. Salcic.  High-speed customizable fuzzy-logic processor: architecture and implementation , 2001, IEEE Trans. Syst. Man Cybern. Part A.

[33]  Zhi-Qiang Liu,et al.  Fuzzy neural network in case-based diagnostic system , 1997, IEEE Trans. Fuzzy Syst..

[34]  Robert K. Brayton,et al.  ESPRESSO-SIGNATURE: A New Exact Minimizer for Logic Functions , 1993, 30th ACM/IEEE Design Automation Conference.

[35]  Witold Pedrycz,et al.  A reconfigurable fuzzy neural network with in-situ learning , 1995, IEEE Micro.

[36]  Fan Yang,et al.  Implementation of an RBF neural network on embedded systems: real-time face tracking and identity verification , 2003, IEEE Trans. Neural Networks.

[37]  Christopher J. Merz,et al.  UCI Repository of Machine Learning Databases , 1996 .

[38]  Rosangela Ballini.  Equality index and learning in recurrent fuzzy neural networks , 2003, The 12th IEEE International Conference on Fuzzy Systems, 2003. FUZZ '03..

[39]  A. Stoica,et al.  Synaptic and somatic operators for fuzzy neurons: which t-norms to choose? , 1996, Proceedings of North American Fuzzy Information Processing.

[40]  Frank Vahid,et al.  On-chip logic minimization , 2003, Proceedings 2003. Design Automation Conference (IEEE Cat. No.03CH37451).

[41]  Jonathan Wayne Mills,et al.  Lukasiewicz logic arrays , 1990, Proceedings of the Twentieth International Symposium on Multiple-Valued Logic.

[42]  Hiroomi Hikawa,et al.  A digital hardware pulse-mode neuron with piecewise linear activation function , 2003, IEEE Trans. Neural Networks.

[43]  W. Pedrycz,et al.  An introduction to fuzzy sets : analysis and design , 1998 .

[44]  Witold Pedrycz,et al.  Fuzzy modelling through logic optimization , 2005, NAFIPS 2005 - 2005 Annual Meeting of the North American Fuzzy Information Processing Society.

[45]  Ángel Rodríguez-Vázquez,et al.  Neuro-fuzzy chip to handle complex tasks with analog performance , 2003, IEEE Trans. Neural Networks.