The Community for Technology Leaders
RSS Icon
Subscribe
Issue No.08 - Aug. (2013 vol.62)
pp: 1597-1606
M. Soltiz , Dept. of Comput. Eng., Rochester Inst. of Technol., Rochester, NY, USA
D. Kudithipudi , Dept. of Comput. Eng., Rochester Inst. of Technol., Rochester, NY, USA
C. Merkel , Dept. of Comput. Eng., Rochester Inst. of Technol., Rochester, NY, USA
G. S. Rose , Trusted Syst. Branch, Air Force Res. Lab./RITA, Rome, NY, USA
R. E. Pino , ICF Int., Fairfax, VA, USA
ABSTRACT
Neural logic blocks (NLBs) enable the realization of biologically inspired reconfigurable hardware. Networks of NLBs can be trained to perform complex computations such as multilevel Boolean logic and optical character recognition (OCR) in an area- and energy-efficient manner. Recently, several groups have proposed perceptron-based NLB designs with thin-film memristor synapses. These designs are implemented using a static threshold activation function, limiting the set of learnable functions to be linearly separable. In this work, we propose two NLB designs-robust adaptive NLB (RANLB) and multithreshold NLB (MTNLB)-which overcome this limitation by allowing the effective activation function to be adapted during the training process. Consequently, both designs enable any logic function to be implemented in a single-layer NLB network. The proposed NLBs are designed, simulated, and trained to implement ISCAS-85 benchmark circuits, as well as OCR. The MTNLB achieves 90 percent improvement in the energy delay product (EDP) over lookup table (LUT)-based implementations of the ISCAS-85 benchmarks and up to a 99 percent improvement over a previous NLB implementation. As a compromise, the RANLB provides a smaller EDP improvement, but has an average training time of only ≈ 4 cycles for 4-input logic functions, compared to the MTNLBs ≈ 8-cycle average training time.
INDEX TERMS
transfer functions, benchmark testing, biocomputing, logic design, memristors, optical character recognition, perceptrons, power aware computing, reconfigurable architectures, table lookup,4-input logic functions, memristor-based neural logic blocks, nonlinearly separable functions, biologically inspired reconfigurable hardware realization, perceptron-based NLB designs, thin-film memristor synapses, static threshold activation function, robust adaptive NLB, RANLB, multithreshold NLB, MTNLB, training process, logic function, single-layer NLB network, ISCAS-85 benchmark circuits, OCR, optical character recognition, multilevel Boolean logic, energy delay product, EDP, lookup table, LUT-based implementations, ISCAS-85 benchmarks,Self-organizing networks, Neural networks, Biological system modeling,neural networks, Neuromorphic, stochastic gradient descent, memristors, OCR, reconfigurable logic
CITATION
M. Soltiz, D. Kudithipudi, C. Merkel, G. S. Rose, R. E. Pino, "Memristor-Based Neural Logic Blocks for Nonlinearly Separable Functions", IEEE Transactions on Computers, vol.62, no. 8, pp. 1597-1606, Aug. 2013, doi:10.1109/TC.2013.75
REFERENCES
[1] C. Mead, "Neuromorphic Electronic Systems," Proc. IEEE, vol. 78, no. 10, pp. 1629-1636, Oct. 1990.
[2] D.A. Drachman, "Do We Have Brain to Spare?" Neurology, vol. 64, no. 12, pp. 2056-2062, http://www.ncbi.nlm.nih.gov/pubmed15985565 , 2005.
[3] G.S. Snider, "Spike-Timing-Dependent Learning in Memristive Nanodevices," Proc. IEEE Int'l Symp. Nanoscale Architectures, pp. 85-92, 2008.
[4] C. Zamarreño Ramos, L.A. Camuñas Mesa, J.A. Pérez-Carrasco, T. Masquelier, T. Serrano-Gotarredona, and B. Linares-Barranco, "On Spike-Timing-Dependent-Plasticity, Memristive Devices, and Building a Self-Learning Visual Cortex," Frontiers in Neuroscience, vol. 5, p. 26, 2011.
[5] S.H. Jo, T. Chang, I. Ebong, B.B. Bhadviya, P. Mazumder, and W. Lu, "Nanoscale Memristor Device as Synapse in Neuromorphic Systems," Nano letters, vol. 10, no. 4, pp. 1297-301, http://www.ncbi.nlm.nih.gov/pubmed20192230 , Apr. 2010.
[6] D. Chabi, W. Zhao, D. Querlioz, and J.-o. Klein, "Robust Neural Logic Block ( NLB ) Based on Memristor Crossbar Array," Proc. IEEE/ACM Int'l Symp. Nanoscale Architectures (NANOARCH), pp. 137-143, 2011.
[7] K.K. Likharev, "Neuromorphic CMOL Circuits," Nanotechnology, vol. 1, pp. 339-342, 2003.
[8] H. Manem, J. Rajendran, and G.S. Rose, "Stochastic Gradient Descent Inspired Training Technique for a CMOS / Nano Memristive Trainable Threshold Gate Array," IEEE Trans. Circuits and Systems, vol. 59, no. 5, pp. 1051-1060, May 2012.
[9] I. Ebong and P. Mazumder, "CMOS and Memristor-Based Neural Network Design for Position Detection," Proc. IEEE, vol. 100, no. 6, pp. 2050-2060, June 2012.
[10] B.L. Mouttet, "Crossbar Control Circuit," Patent US 7 609 086, Oct. 2009.
[11] B. Mouttet, "Proposal for Memristors in Signal Processing," Proc. Int'l Conf. Inst. of Computer Science Informatics and Telecomm. Eng. (Nano-Net), pp. 11-13, 2009.
[12] E. Farquhar, C. Gordon, and P. Hasler, "A Field Programmable Neural Array," Proc. IEEE Int'l Symp. Circuits and Systems (ISCAS '06), pp. 4117-4120, May 2006.
[13] G. Scheler, "Memorization in a Neural Network with Adjustable Transfer Function and Conditional Gating," Quantitative Biology, vol. 1, 2004.
[14] G. Scheler, "Regulation of Neuromodulator Receptor Efficacy - Implications for Whole-Neuron and Synaptic Plasticity," Progress in Neurobiology, vol. 72, no. 6, pp. 399-415, 2004.
[15] G.S. Rose, R. Pino, and Q. Wu, "A Low-Power Memristive Neuromorphic Circuit Utilizing a Global/Local Training Mechanism," Proc. Int'l Joint Conf. Neural Networks (IJCNN), pp. 2080-2086, 2011.
[16] T. Goh, P. Wang, and H. Lui, "Learning Algorithm for the Enhanced Fuzzy Perceptron," Proc. Int'l Joint Conf. Neural Networks (IJCNN), pp. 435-440, 1992.
[17] D. Palmer-Brown and M. Kang, "ADFUNN : An Adaptive Function Neural Network," Proc. Seventh Int'l Conf. Adaptive and Natural Computing Algorithms (ICANNGA '05), 2005.
[18] M. Sahami, "Learning Non-Linearly Separable Boolean Functions with Linear Threshold Unit Trees and Madaline-Style Networks," Proc. 11th Nat'l Conf. Artificial Intelligence, pp. 335-341, 1993.
[19] W. Wang, T.T. Jing, and B. Butcher, "FPGA Based on Integration of Memristors and CMOS Devices," Proc. IEEE Int'l Symp. Circuits and Systems (ISCAS), pp. 1963-1966, 2010.
[20] M. Soltiz, C. Merkel, D. Kudithipudi, and G.S. Rose, "RRAM-Based Adaptive Neural Logic Block for Implementing Non-Linearly Separable Functions in a Single Layer," Proc. IEEE/ACM Int'l Symp. Nanoscale Architectures (NANOARCH '12), 2012.
[21] D.B. Strukov, G.S. Snider, D.R. Stewart, and R.S. Williams, "The Missing Memristor Found," Nature, vol. 453, pp. 80-83, 2008.
[22] T. Roska and L. Chua, "The CNN Universal Machine: An Analogic Array Computer," IEEE Trans. Circuits and Systems II: Analog and Digital Signal Processing, vol. 40, no. 3, pp. 163-173, Mar. 1993.
[23] M. Hansen, "Unveiling the ISCAS-85 Benchmarks: A Case Study in Reverse Engineering," IEEE Design & Test of Computers, vol. 16, no. 3, pp. 72-80, July 1999.
[24] P. Chong Sis 1.3 Unofficial Distribution, http://embedded.eecs. berkeley.edu/Alumni/ pchongsis.html, 2013.
[25] A. Rajavelu, M. Musavi, and M. Shirvaikar, "A Neural Network Approach to Character Recognition," Neural Networks, vol. 2, no. 5, pp. 387-393, 1989.
[26] B. Hussain and M. Kabuka, "A Novel Feature Recognition Neural Network and Its Application to Character Recognition," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 16, no. 1, pp. 98-106, Jan. 1994.
[27] O.D. Trier, A.K. Jain, and T. Taxt, "Feature Extraction Methods for Character Recognition- A Survey," Pattern Recognition, vol. 29, no. 4, pp. 641-662, 1996.
[28] http://qnetv2k.com/Qnet2000Manual/htmlqnet65ym.htm , 2013.
27 ms
(Ver 2.0)

Marketing Automation Platform Marketing Automation Tool