Memristor-based reservoir computing

As feature-size scaling and “Moore's Law” in integrated CMOS circuits further slows down, attention is shifting to computing by non-von Neumann and non-Boolean computing models. Reservoir computing (RC) is a new computing paradigm that allows to harness the intrinsic dynamics of a “reservoir” to perform useful computations. The reservoir, or compute core, must only provide sufficiently rich dynamics that are then mapped onto a low-dimensional space by an readout layer. One of the key advantages of this approach is that only the readout layer needs to be adapted to perform the desired computation. The reservoir itself remains unchanged. In this paper we use for the first time memristive components as reservoir building blocks that are assembled into device networks. Memristive components are particularly interesting for this purpose because of their non-linear and memory characteristics. In addition, they can be integrated very densely and provide rich dynamics with a few components only. We use pattern recognition and associative memory tasks to illustrate the memristive reservoir computing approach. For that purpose, we have built a software framework that allows to create valid memristor networks, to simulate and evaluate them in Ngspice, and to train the readout layer by means of a Genetic Algorithm (GA). Our results show that we can efficiently and robustly classify temporal patterns. The approach presents a promising new computing paradigm that harnesses the non-linear, time-dependent, and highly-variable properties of current memristive components for solving computational tasks.

[1]  Herbert Jaeger,et al.  Reservoir computing approaches to recurrent neural network training , 2009, Comput. Sci. Rev..

[2]  S. Barry Cooper,et al.  Computability In Context: Computation and Logic in the Real World , 2009 .

[3]  Scott Hauck,et al.  The Future of Integrated Circuits: A Survey of Nanoelectronics , 2010, Proceedings of the IEEE.

[4]  György Cserey,et al.  Macromodeling of the Memristor in SPICE , 2010, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

[5]  James A. Anderson,et al.  An Introduction To Neural Networks , 1998 .

[6]  Samiha Mourad,et al.  Digital Logic Implementation in Memristor-Based Crossbars - A Tutorial , 2010, 2010 Fifth IEEE International Symposium on Electronic Design, Test & Applications.

[7]  Paul D. Franzon,et al.  Nanocell logic gates for molecular computing , 2002 .

[8]  José Carlos Príncipe,et al.  Special issue on echo state networks and liquid state machines , 2007, Neural Networks.

[9]  D. Stewart,et al.  The missing memristor found , 2008, Nature.

[10]  Henry Markram,et al.  Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations , 2002, Neural Computation.

[11]  John R. Anderson.  Language, Memory, and Thought , 1976 .

[12]  Benjamin Schrauwen,et al.  Toward optical signal processing using photonic reservoir computing. , 2008, Optics express.

[13]  Ben Jones,et al.  Is there a Liquid State Machine in the Bacterium Escherichia Coli? , 2007, 2007 IEEE Symposium on Artificial Life.

[14]  Sudeshna Sinha,et al.  Introduction to focus issue: intrinsic and designed computation: information processing in dynamical systems--beyond the digital hegemony. , 2010, Chaos.

[15]  I. Pavlov.  Conditioned Reflexes: An Investigation of the Physiological Activity of the Cerebral Cortex , 1929 .

[16]  James A. M. McHugh,et al.  Synthesis of biconnected graphs , 1974 .

[17]  L. Chua.  Memristor-The missing circuit element , 1971 .

[18]  D. Batas,et al.  A Memristor SPICE Implementation and a New Approach for Magnetic Flux-Controlled Memristor Modeling , 2011, IEEE Transactions on Nanotechnology.

[19]  Benjamin Schrauwen,et al.  Compact hardware liquid state machines on FPGA for real-time speech recognition , 2008, Neural Networks.

[20]  Massoud Pedram,et al.  Architectures for silicon nanoelectronics and beyond , 2007, Computer.

[21]  Herbert Jaeger,et al.  The''echo state''approach to analysing and training recurrent neural networks , 2001 .

[22]  Terrence J. Sejnowski,et al.  What Makes a Dynamical System Computationally Powerful , 2007 .

[23]  John J. Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities , 1999 .

[24]  Min Jiang,et al.  Automated synthesis of passive analog filters using graph representation , 2010, Expert Syst. Appl..

[25]  Christof Teuscher,et al.  Evolving nanoscale associative memories with memristors , 2011, 2011 11th IEEE International Conference on Nanotechnology.

[26]  W. Maass,et al.  What makes a dynamical system computationally powerful ? , 2022 .

[27]  T. A. Wey,et al.  Amplitude modulator circuit featuring TiO2 memristor with linear dopant drift , 2009 .

[28]  Christof Teuscher.  On Irregular Interconnect Fabrics for Self-Assembled Nanoscale Electronics , 2006 .

[29]  Warren Robinett,et al.  Memristor-CMOS hybrid integrated circuits for reconfigurable logic. , 2009, Nano letters.

[30]  Chrisantha Fernando,et al.  Pattern Recognition in a Bucket , 2003, ECAL.

[31]  A.N. Michel,et al.  Associative memories via artificial neural networks , 1990, IEEE Control Systems Magazine.

[32]  Massimiliano Di Ventra,et al.  Experimental demonstration of associative memory with memristive neural networks , 2009, Neural Networks.

[33]  I. Pavlov,et al.  Conditioned reflexes: An investigation of the physiological activity of the cerebral cortex , 2010, Annals of Neurosciences.

[34]  Henry Markram,et al.  Computational models for generic cortical microcircuits , 2004 .

[35]  Marco Tomassini,et al.  Soft computing - integrating evolutionary, neural, and fuzzy systems , 2001 .

[36]  Dmitri B Strukov,et al.  Four-dimensional address topology for circuits with stacked multilayer crossbar arrays , 2009, Proceedings of the National Academy of Sciences.

[37]  Benjamin Schrauwen,et al.  Optoelectronic Reservoir Computing , 2011, Scientific Reports.

[38]  R. Williams,et al.  How We Found The Missing Memristor , 2008, IEEE Spectrum.

[39]  Dalibor Biolek,et al.  SPICE Model of Memristor with Nonlinear Dopant Drift , 2009 .

[40]  Benjamin Schrauwen,et al.  Connectivity, Dynamics, and Memory in Reservoir Computing with Binary and Analog Neurons , 2010, Neural Computation.

[41]  Henry Markram,et al.  A New Approach towards Vision Suggested by Biologically Realistic Neural Microcircuit Models , 2002, Biologically Motivated Computer Vision.

[42]  David H. Wolpert,et al.  Adaptive Programming of Unconventional Nano-Architectures , 2006, cond-mat/0609489.

[43]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation (3rd Edition) , 2007 .

[44]  V.V. Zhirnov,et al.  New Frontiers: Self-Assembly and Nanoelectronics , 2001, Computer.

[45]  Sudeshna Sinha,et al.  Chaogates: morphing logic gates that exploit dynamical patterns. , 2010, Chaos.

[46]  Darko Stefanovic,et al.  Deoxyribozyme-based three-input logic gates and construction of a molecular full adder. , 2006, Biochemistry.