Adaptive Resonance Theory Design in Mixed Memristive-Fuzzy Hardware
Fuzzification of neural networks show great promise in improving system reliability and computational efficiency. In the present work we explore the possibility of combining fuzzy inference with Adaptive Resonance Theory (ART) neural networks implemented on massively parallel hardware architectures including memristive devices. Memristive hardware holds promise to greatly reduce power requirements of such neuromorphic applications by increasing synaptic memory storage capacity and decreasing wiring length between memory storage and computational modules. Storing and updating synaptic weight values based on synaptic plasticity rules is one of the most computationally demanding operations in biologically-inspired neural networks such as Adaptive Resonance Theory (ART). Our work indicates that Fuzzy Inference Systems (FIS) can significantly improve computational efficiency. In this chapter, we introduce a novel method, based on fuzzy inference, to reduce the computational burden of a class of recurrent networks named recurrent competitive fields (RCFs). A novel algorithmic scheme is presented to more efficiently perform the synaptic learning component of ART networks in memristive hardware. RCF networks using FIS are able to learn synaptic weightswith small absolute error rates, and classify correctly. Using the FIS methodology it is possible to significantly reduce the computational complexity of the proposed memristive hardware using computationally cheaper and more robust fuzzy operators.
The authors gratefully acknowledge helpful conversations with Anatoli Gorchetchnikov, as well as financial support from the DARPA Synapse Program, the National Science Foundation, the Missouri S&T Intelligent Systems Center, and the Mary K. Finley Missouri endowment. Max Versace (email@example.com) is the Director of the Boston University Neuromorphics Lab and was supported in part by the Center of Excellence for Learning in Education, Science and Technology (CELEST), a National Science Foundation Science of Learning Center (NSF SBE-0354378 and NSF OMA-0835976). This work was also partially funded by the DARPA SyNAPSE program, contract HR0011-09-3-0001.
- 10.Merrikh-Bayat F, Shouraki SB (2011) Efficient neuro-fuzzy system and its memristor crossbar-based hardware implementation. CoRR, abs/1103.1156, 2011Google Scholar
- 11.Merrikh-Bayat F, Shouraki SB (2011) Memristor crossbar-based hardware implementation of fuzzy membership functions. CoRR, abs/1009.0896, 2011Google Scholar
- 12.Klimo M, Such O (2011) Memristors can implement fuzzy logic. CoRR, abs/1110.2074, 2011Google Scholar
- 14.Zhong QS, Yu Y-B, Yu J-B (2010) Fuzzy modeling and impulsive control of a memristor-based chaotic system. Chin Phys Lett 27(2) (art. no. 020501)Google Scholar
- 16.Kogge P (2011) The tops in FLOPS. Spectrum, IEEE, 2011Google Scholar
- 18.Grossberg S (1982) Contour enhancement, short term memory, and constancies in reverberating neural networks. Studies of mind and brain (Chapter 8). Kluwer/Reidel Press, BostonGoogle Scholar
- 19.Sugeno M (1985) Industrial applications of fuzzy control. Elsevier, OxfordGoogle Scholar
- 24.Versace M, Chandler B (2011) MoNETA: a mind made from memristors. IEEE Spectrum, December 2011Google Scholar
- 26.Pazienza G, Kozma R (2011) Memristor as an archetype of dynamic data-driven systems and applications to sensor networks. Dynamic data driven application systems, DDDAS 2011, Tsukuba, Japan, June 2–3 2011Google Scholar
- 27.Bezdek JC, Keller J, Krisnapuram R, Pal N (2005) Fuzzy models and algorithms for pattern recognition and image processing. Springer, New YorkGoogle Scholar
- 28.Kosko B (1999) The fuzzy future: from society and science to heaven in a chip. Harmony Books, New YorkGoogle Scholar
- 33.Anagnostopoulos G, Georgiopoulos M (2001) Ellipsoid ART and ARTMAP for incremental unsupervised and supervised learning. In: Proceedings of the international joint conference on neural networks, vol 2, pp 1221–1226, 2001Google Scholar
- 34.Carpenter G (2003) Default ARTMAP. In: Proceedings of the international conference on neural networks, pp 1396–1401, 2003Google Scholar