Realization of the conscience mechanism in cmos implementation of winner-takes-all self-organizing neural networks

IEEE Transactions on Neural Networks

Volumn 21, Issue 6, 2010, Pages 961-971

  Dlugosz, Rafal ^a   Talaśka, Tomasz ^b   Pedrycz, Witold ^c,d   Wojtyna, Ryszard ^b  

^a EPFL   (Switzerland)

^b UNIVERSITY OF TECHNOLOGY AND LIFE SCIENCES   (Poland)

^c UNIVERSITY OF ALBERTA   (Canada)

^d SYSTEMS RESEARCH INSTITUTE   (Poland)

Author keywords

Analog circuits; Complementary metal?oxide?semiconductor (CMOS) implementation; Conscience mechanism; Low energy consumption; Parallel data processing; Self organizing map (SOM); Winner takes all (WTA) neural networks

Indexed keywords

COMPLEMENTARY METAL?OXIDE?SEMICONDUCTOR (CMOS) IMPLEMENTATION; CONSCIENCE MECHANISM; LOW ENERGY CONSUMPTION; PARALLEL DATA PROCESSING; WINNER-TAKES-ALL (WTA) NEURAL NETWORKS;

ANALOG CIRCUITS; BIOELECTRIC PHENOMENA; CMOS INTEGRATED CIRCUITS; COMPUTER SIMULATION; CONFORMAL MAPPING; DATA PROCESSING; ELECTRIC NETWORK ANALYSIS; MATLAB; NETWORK PERFORMANCE; NEURONS; STRENGTH OF MATERIALS; SYSTEMS ANALYSIS;

NEURAL NETWORKS;

ARTICLE; ARTIFICIAL NEURAL NETWORK; AUTOMATED PATTERN RECOGNITION; COMPUTER SIMULATION; CONSCIENCE; GAME; HUMAN; LEARNING; METHODOLOGY; NERVE CELL; PHYSIOLOGY; SEMICONDUCTOR;

COMPUTER SIMULATION; CONSCIENCE; GAME THEORY; HUMANS; LEARNING; NEURAL NETWORKS (COMPUTER); NEURONS; PATTERN RECOGNITION, AUTOMATED; TRANSISTORS, ELECTRONIC;

EID: 77953113958     PISSN: 10459227     EISSN: None     Source Type: Journal    
DOI: 10.1109/TNN.2010.2046497     Document Type: Article

References (34)

1. G. Cauwenberghs, M. A. Bayoumi, and E. Sanchez-Sinencio, Learning on Silicon: Adaptive VLSI Neural Systems. Norwell, MA: Kluwer, 1999.
2. S. Fakhraie and K. C. Smith, VLSI-Compatible Implementations for Artificial Neural Networks. Norwell, MA: Kluwer, 1997.
3. B. Linares-Barranco, E. Sanchez-Sinencio, A. Rodriguez-Vazquez, and J. L. Huertas, "A CMOS analog adaptive BAM with on-chip learning and weight refreshing," IEEE Trans. Neural Netw., vol.4, no.3, pp. 445-455, May 1993.
4. J. Choi, S. H. Bang, and B. J. Sheu, "A programmable analog VLSI neural network processor for communication receivers," IEEE Trans. Neural Netw., vol.4, no.3, pp. 484-495, May 1993. (Pubitemid 23684032)
5. H. Hikawa, "Frequency-based multilayer neural network with on-chip learning," IEEE Trans. Neural Netw., vol.10, no.3, pp. 545-553, May 1999.
6. R. Coggins, M. Jabri, B. Flower, and S. Pickard, "A hybrid analog and digital VLSI neural network for intracardiac morphology classification, " IEEE J. Solid-State Circuits, vol.30, no.5, pp. 542-550, May 1995.
7. C. Mead, Analog VLSI and Neural Systems. Reading, MA: Addison-Wesley, 1989.
8. M. Holler, S. Tam, H. Castro, and R. Benson, "An electrically trainable artificial neural network (ETANN) with 10240 'Floating gate' synapses," in Proc. Int. Joint Conf. Neural Netw.,Washington, DC, Jun. 1998, pp. 191-196.
9. H. C. Card, D. K. McNeill, and C. R. Schneider, "Analog VLSI circuits for competitive learning networks," Analog Integr. Circuits Signal Process., vol.15, no.3, pp. 291-314, Mar. 1998.
10. T. Talaśka, R. Długosz, W. Wojtyna, K. Iniewski, and W. Pedrycz, "Analog-counter-based conscience mechanism in Kohonen's neural network implemented in CMOS 0.18 μm technology," in Proc. IEEE Workshop Signal Process. Syst. Design Implement., Banff, AB, Canada, Oct. 2006, pp. 416-421.
11. T. Talaśka, R. Długosz, and W. Pedrycz, "Adaptive weight change mechanism for Kohonens's neural network implemented in CMOS 0.18 μm technology," in Proc. Eur. Symp. Artif. Neural Netw., Bruges, Belgium, Apr. 2007, pp. 151-156.
12. T. Talaśka and R. Długosz, "Initialization mechanism in Kohonen neural network implemented in CMOS technology," in Proc. Eur. Symp. Artif. Neural Netw., Bruges, Belgium, Apr. 2008, pp. 337-342.
13. T. Talaśka, R. Długosz, J. Dalecki, and R.Wojtyna, "Experimental Kohonen neural network implemented in CMOS 0.18 μm technology," in Proc. Int. Conf. Mixed Design Integr. Circuits Syst., Poznań, Poland, Jun. 2008, pp. 243-248.
14. T. Kohonen, Self-Organizing Maps, 3rd ed. Berlin, Germany: Springer-Verlag, 2001.
15. R. Rizzo and A. Chella, "A comparison between habituation and conscience mechanism in self-organizing maps," IEEE Trans. Neural Netw., vol.17, no.3, pp. 807-810, May 2006.
16. S. C. Ahalt, A. K. Krishnamurthy, P. Chen, and D. E. Melton, "Competitive learning algorithms for vector quantization," Neural Netw., vol.3, pp. 277-290, 1990.
17. D. E. Rumelhart and D. Zipser, "Feature discovery by competitive learning," Cogn. Sci., vol.9, no.1, pp. 75-112, Jan.-Mar. 1985.
18. D. DeSieno, "Adding a conscience to competitive learning," in Proc. IEEE Conf. Neural Netw., San Diego, CA, Jul. 1988, vol.1, pp. 117-124.
19. L. Gatet, H. Tap-Béteille, and F. Bony, "Comparison between analog and digital neural network implementations for range-finding applications," IEEE Trans. Neural Netw., vol.20, no.3, pp. 460-470, Mar. 2009.
20. W. Zhang, S. Jing, L. Gui, and Y. Zhang, "Physiological data acquisition system for education assessment using wireless sensor network," in Proc. Int. Conf. Technol. Appl., Shenzhen, China, May 2008, pp. 471-473.
21. S.-L. Chen, H.-Y. Lee, Y.-W. Chu, C.-A. Chen, C.-C. Lin, and C.-H. Luo, "A variable control system for wireless body sensor network," in Proc. IEEE Int. Symp. Circuits Syst., Seattle, WA, May 2008, pp. 2034-2037.
22. G. Thimm and E. Fiesler, "Neural network initialization," in From Neural to Artificial Neural Computation. Berlin, Germany: Springer-Verlag, 1995, vol.930, pp. 535-542, DOI: 10.1007/3-540-59497-3-220, ISSN: 0302-9743, ISBN: 978-3-540-59497-0.
23. Y. Chen and F. Bastani, "ANN with two-dendrite neurons and its weight initialization," in Proc. Int. Joint Conf. Neural Netw., Baltimore, MD, Jun. 1992, pp. 139-146.
24. A. Rajah and M. H. Khalil, "ASIC design of a Kohonen neural network microchip," in Proc. IEEE Int. Conf. Semicond. Electron., Kuala Lumpur, Malaysia, Dec. 2004, pp. 148-151.
25. C.-Y. Wu and W.-K. Kuo, "A new analog implementation of the Kohonen neural network," in Proc. Int. Symp. VLSI Technol. Systems Appl., Taipei, Taiwan, May 1993, pp. 262-266.
26. D. Macq, M. Verleysen, and P. J.-D. Legat, "Analog implementation of a Kohonen map with on-chip learning," IEEE Trans. Neural Netw., vol.4, no.3, pp. 456-461, May 1993.
27. T. Talaśka and R. Długosz, "Current mode Euclidean distance calculation circuit for Kohonen's neural network implemented in CMOS 0.18 μm technology," in Proc. IEEE Can. Conf. Electr. Comput. Eng., Vancouver, "C, Canada, Apr. 2007, pp. 437-440.
28. R.Wojtyna and T. Talaśka, "Improved power-saving synapse for adaptive neuroprocessing on silicon," in Proc. IEEE Int. Conf. Signals Electron. Syst., Poznań, Poland, Sep. 2004, pp. 27-30.
29. P. Somervuo and T. Kohonen, "Self-organizing maps and learning vector quantization for feature sequences," Neural Process. Lett., vol.10, no.2, pp. 151-159, Oct. 1999.
30. J. A. Croon, M. Rosmeulen, S. Decoutere, W. Sansen, and H. E. Maes, "An easy-to-use mismatch model for the MOS transistor," Int. J. Solid-State Circuits, vol.37, no.8, pp. 1056-1064, Aug. 2002.
31. C.-H. Chang, P. Xu, R. Xiao, and T. Srikanthan, "New adaptive color quantization method based on self-organizing maps," IEEE Trans. Neural Netw., vol.16, pp. 237-249, Jan. 2005.
32. R. Długosz and M. Kolasa, "CMOS programmable asynchronous neighborhood mechanism for WTM Kohonen neural network," in Proc. Int. Conf. Mixed Design Integr. Circuits Syst., Poznań, Poland, Jun. 2008, pp. 197-201.
33. M. Kolasa and R. Długosz, "Parallel asynchronous neighborhood mechanism for WTM Kohonen network implemented in CMOS technology," in Proc. Eur. Symp. Artif. Neural Netw., Bruges, Belgium, Apr. 2008, pp. 331-336.
34. R. Długosz and T. Talaśka, "Low power current-mode binary-tree asynchronous Min/Max circuit," Microelectron. J., vol.41, no.1, pp. 64-73, Jan. 2010.