Abstract
Neural Networks perform computationally intensive tasks offering smart solutions for many new media applications. A number of analog and mixed digital/analog implementations have been proposed to smooth the algorithmic gap. But gradually, the digital implementation has become feasible, and the dedicated neural processor is on the horizon. A notable example is the Cellular Neural Network (CNN). The analog direction has matured for low-power, smart vision sensors; the digital direction is gradually being shaped into an IP-core for algorithm acceleration, especially for use in FPGA-based high-performance systems. The chapter discusses the next step towards a flexible and scalable multi-core engine using Application-Specific Integrated Processors (ASIP). This topographic engine can serve many new media tasks, as illustrated by novel applications in Homeland Security. We conclude with a view on the CNN kaleidoscope for the year 2020.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Hennessy, J.L., Patterson, D.A.: Computer Architecture: A Quantitative Approach, 4th edn. Morgan Kaufmann, San Francisco (2007)
Tummala, R.R.: Moore’s law meets its match. IEEE Spectr. 43(6), 44 (2006)
von Neumann, J.: The general and logical theory of automata. In: Newman, J.R. (ed.) The World of Mathematics, pp. 2070–2089. Simon and Schuster, New York (1954). Reprinted by Dover Publications (2000)
Malki, S.: On hardware implementation of discrete-time cellular neural networks. Ph.D. Thesis, Lund University, Sweden (2008)
Zhirnov, V., Cavin, R., Leeming, G., Galatsis, K.: An assessment of integrated digital cellular automata architectures. IEEE Comput. 41(1), 38 (2008)
Domínguez-Castro, R., Espejo, S., Rodríguez-Vázquez, A., Carmona, R.: A CNN universal chip in CMOS technology. In: Proceedings 3rd IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA-94), Rome, pp. 91–96, December 1994
Haykin, S.: Neural Networks: A Comprehensive Foundation. Macmillan, New York (1994)
Keegstra, H., Jansen, W.J., Nijhuis, J.A.G., Spaanenburg, L., Stevens, J.H., Udding, J.T.: Exploiting network redundancy for lowest–cost neural network realizations. In: Proceedings IEEE International Conference on Neural Networks, ICNN ’96, vol. 2, Washington, DC, pp. 951–955 (1996)
Hornik, K., Stinchcombe, M., White, H.: Multilayer feedforward networks are universal approximators. Neural Netw. 2, 359 (1989)
Spaanenburg, L., Malki, S.: Artificial life goes ‘in-silico’. In: Proceedings 2005 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications, CIMSA 2005, Giardini Naxos, Taormina, Sicily, Italy, pp. 267–272, 20–22 July 2005
Chua, L.O., Yang, L.: Cellular neural networks: theory. IEEE Trans. Circuits Syst. 35, 1257–1273 (1988)
ter Brugge, M.H.: Morphological design of discrete-time cellular neural networks. Ph.D. Thesis, Rijksuniversiteit Groningen, Netherlands (2004)
Uchimoto, T., Hjime, H., Tanji, Y., Tanaka, M.: Design of DTCNN image processing (Japanese). Transactions of the Institute of Electronics, Information and Communication Engineers J84-D-2, 1464–1471 (2001)
Harrer, H., Nossek, J.A.: Discrete-time cellular neural networks. Int. J. Circuit Theory Appl. 20, 453 (1992)
Domínguez-Castro, R., et al.: A 0.8 μm CMOS two-dimensional programmable mixed-signal focal-plane array processor with on-chip binary imaging and instructions storage. IEEE J. Solid-St. Circ. 32, 1013 (1997)
Espejo, S., Domínguez-Castro, R., Liñán, G., Rodríguez-Vázquez, A.: A 64 × 64 CNN universal chip with analog and digital I/O. In: Proceedings 1998 IEEE International Conference on Electronics, Circuits and Systems (ICECS98), Lisbon, pp. 203–206 (1998)
Liñán, G., Espejo, S., Domínguez-Castro, R., Roca, E., Rodríguez-Vázquez, A.: CNNUC3: a mixed-signal 64 × 64 CNN universal chip. In: Proceedings 7th International Conference on Microelectronics for Neural, Fuzzy and Bio-Inspired Systems (MicroNeuro-99), IEEE, Piscataway, NJ, pp. 61–68 (1999)
Liñán, G., Espejo, S., Domínguez-Castro, R., Rodríguez-Vázquez, A.: ACE4k: an analog I/O 64 × 64 visual microprocessor chip with 7-bit analog accuracy. Int. J. Circuit Theory Appl. 30, 89 (2002)
Rodríguez-Vázquez, A., Liñán-Cembrano, G., Carranza, L., Roca-Moreno, E., Carmona-Galan, R., Jimenez-Garrido, F., Domínguez-Castro, R., Espejo Meana, S.: ACE16k: the third generation of mixed-signal SIMD-CNN ACE chips toward VSoCs. IEEE Trans. Circuits Syst., I: Regul. Pap. 51, 851 (2004)
Liñán, G., Rodríguez-Vázquez, A., Espejo, S., Domínguez-Castro, R.: ACE16k: A 128 × 128 focal plane analog processor with digital I/O. In: Proceedings of the 7th IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA 2002), Frankfurt, Germany, pp.132–139, July 2002
Liñán, G., Foldesy, P., Espejo, S., Domínguez-Castro, R., Rodríguez-Vázquez, A.: A 0.5 μm CMOS 106 transistors analog programmable array processor for real-time image processing. In: Proceedings 25th European Solid-State Circuits Conference ESSCIRC ’99, Stresa (Italy), pp. 358–361
Delbrück, T., Mead, C.A.: Analog VLSI phototransduction by continuous-time, adaptive, logarithmic photoreceptor circuits. California Institute Technology, Computation and Neural Systems Program, Tech. Rep. CNS Memo no. 30, Pasadena, May (1994)
Rodríguez-Vázquez, A., Espejo, S., Domínguez-Castro, R., Huertas, J.L., Sanchez-Sinencio, E.: Current-mode techniques for the implementation of continuous- and discrete-time cellular neural networks. IEEE Trans. Circuits Syst. II: Analog Dig. Signal Process. 40, 132 (1993)
Espejo, S., Rodríguez-Vázquez, A., Domínguez-Castro, R., Carmona, R.: Convergence and stability of the FSR CNN model. In: Proceedings 3rd IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA-94), Rome, pp. 411–416 (1994)
Jimenez-Marrufo, A., Mendizdbal, A., Morillas-Castillo, S., Dominguez-Castro, R., Espejo, S., Romay-Judrez, R., Rodriguez-Vazquez, A.: Data matrix code recognition using the Eye-RIS vision system. In: Proceedings IEEE International Symposium on Circuits and Systems, ISCAS 2007, New Orleans, p. 1214
Zarándy, Á., Keresztes, P., Roska, T., Szolgay, P.: An emulated digital architecture implementing the CNN Universal Machine. In: Proceedings 5th IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA-98), London, pp. 249–252 (1998)
Keresztes, P., et al.: An emulated digital CNN implementation. J. VLSI Signal Process 23, 291–303 (1999)
Nagy, Z., Szolgay, P.: Configurable multilayer CNN-UM emulator on FPGA. IEEE Trans. Circuits Syst. I: Fundam. Theory Appl. 50, 774 (2003)
Lopich, A., Dudek, P.: An 80 × 80 general-purpose digital vision chip in 0.18 μm CMOS technology. In: Proceedings IEEE International Symposium on Circuits and Systems, ISCAS 2010, Paris, pp. 4257–4260, May 2010
Alba, L., et al.: New visual sensors and processors. In: Arena, P., Patanè, L. (eds.) Spatial Temporal Patterns for Action-Oriented Perception in Roving Robots. Cognitive Systems Monographs, pp. 351–370. Springer, Berlin/Heidelberg (2009)
Vörösházi, Z., Nagy, Z., Kiss, A., Szolgay, P.: An embedded CNN-UM global analogic programming unit implementation on FPGA. In: Proceedings 10th IEEE International Workshop on Cellular Neural Networks and Their Applications, CNNA ’06, Istanbul, Turkey, Aug 2006. doi: 10.1109/CNNA.2006.341652
Fang, W., Wang, C., Spaanenburg, L.: In search of a robust digital CNN system. In: Proceedings 10th IEEE International Workshop on Cellular Neural Networks and their Applications, CNNA ’06, Istanbul, Turkey, Aug 2006. doi: 10.1109/CNNA.2006.341654
Thiran, P.: Influence of boundary conditions on the behavior of cellular neural networks. IEEE Trans. Circuits and Syst.– I: Fundam. Theory Appl. 40, 207 (1993)
Mirzai, B., Lím, D., Moschytz, G.S.: Robust CNN templates: theory and simulations. In: 4th IEEE International Workshop on Cellular Neural Networks and their Applications, CNNA-96, Seville, Spain, pp. 393–398 (1996)
Grube, R., Dudek, V., Hoefflinger, B., Schau, M.: 0.5 Volt CMOS Logic Delivering 25 Million 16 × 16 Multiplications/s at 400 fJ on a 100 nm T-Gate SOI Technology. Best-Paper Award. IEEE Computer Elements Workshop, Mesa, (2000)
van Drunen, R., Spaanenburg, L., Lucassen, P.G., Nijuis, J.A.G., Udding, J.T.: Arithmetic for relative accuracy. In: Proceedings IEEE Symposium on Computer Arithmetic, ARITH 1995, Bath, England, pp. 239–250 (July 1995)
Spaanenburg, L., Hoefflinger, B, Neusser, S., Nijhuis, J.A.G., Siggelkow, A.: A multiplier-less digital neural network. In: Digest 2nd Int. Conference on Microelectronics of Neural Networks, MicroNeuro 1991, Muenchen, Germany, pp. 281–290 (October 1991)
Zhang, L., Malki, S., Spaanenburg, L.: Intelligent camera cloud computing. In: IEEE International Symposium on Circuits and Systems, ISCAS 2009, Taipei, Taiwan, pp. 1209–1212, May 2009
Chalermsuk, K., Spaanenburg, R.H., Spaanenburg, L., Seuter, M., Stoorvogel, H.: Flexible-length fast Fourier transform for COFDM. In: Proceedings 15th IEEE International Conference on Electronics, Circuits and Systems, ICECS 2008, Malta, pp. 534–537, Aug 2008
Kari, J.: Theory of cellular automata: a survey. Elsevier Theoretical Computer Science 334, 3–33 (2005)
Chua, L.O., Roska T.: The CNN universal machine – Part I: The architecture. In: Proceedings 2nd IEEE Int. workshop on Cellular Neural Networks and their Applications, CNNA-92, Muenich, Germany, pp. 110 (1992)
Roska, T et al.: A hardware accelerator board for Cellular Neural Networks: CNN-HAC. In: Proceedings IEEE Int. workshop on Cellular Neural Networks and their Applications, CNNA-90, Budapest, Hungary, pp. 160–168 (1990)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Spaanenburg, L., Malki, S. (2011). Digital Neural Networks for New Media. In: Hoefflinger, B. (eds) Chips 2020. The Frontiers Collection. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-23096-7_16
Download citation
DOI: https://doi.org/10.1007/978-3-642-23096-7_16
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-22399-0
Online ISBN: 978-3-642-23096-7
eBook Packages: Physics and AstronomyPhysics and Astronomy (R0)