Reservoir Computing Using Networks of CMOS Logic Gates

Reservoir computing is a brain-inspired architecture for machine learning, capable of rapid time series processing. A recurrent neural network called a reservoir is created, and a simple trained readout map is applied to the reservoir state. A real-world dynamical system at the edge of criticality can be used as a reservoir for information processing in place of a software model. In this paper we test the dynamics of a reservoir comprised of discrete digital logic chips on a printed circuit board. The logic gates run freely without a clock, exhibiting complex behavior that expands an input into a higher dimensional representation. By testing these circuits in a dataset-agnostic manner, we identify promising configurations for machine learning. We demonstrate that the reservoir circuit substantially improves the accuracy of a simple classifier on a noisy waveform classification machine learning task.

[1]  Daniel J. Gauthier,et al.  Rapid Time Series Prediction with a Hardware-Based Reservoir Computer , 2018, Chaos.

[2]  Josep L. Rosselló,et al.  FPGA-Based Stochastic Echo State Networks for Time-Series Forecasting , 2015, Comput. Intell. Neurosci..

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

[4]  Daniel Brunner,et al.  Efficient design of hardware-enabled reservoir computing in FPGAs , 2018, Journal of Applied Physics.

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

[6]  S. Kauffman.  Metabolic stability and epigenesis in randomly constructed genetic nets. , 1969, Journal of theoretical biology.

[7]  Lorenzo Livi,et al.  A CHARACTERIZATION OF THE EDGE OF CRITICALITY IN BINARY ECHO STATE NETWORKS , 2018, 2018 IEEE 28th International Workshop on Machine Learning for Signal Processing (MLSP).

[8]  Robert A. Legenstein,et al.  At the Edge of Chaos: Real-time Computations and Self-Organized Criticality in Recurrent Neural Networks , 2004, NIPS.

[9]  Jaideep Pathak,et al.  Model-Free Prediction of Large Spatiotemporally Chaotic Systems from Data: A Reservoir Computing Approach. , 2018, Physical review letters.

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

[11]  Daniel P Lathrop,et al.  Dynamics of analog logic-gate networks for machine learning. , 2019, Chaos.

[12]  M. Ghil,et al.  Boolean delay equations: A simple way of looking at complex systems , 2006, nlin/0612047.

[13]  Julian D. Schwab,et al.  Concepts in Boolean network modeling: What do they all mean? , 2020, Computational and structural biotechnology journal.

[14]  Gunnar Tufte,et al.  Reservoir computing with a chaotic circuit , 2017, ECAL.

[15]  Miguel C. Soriano,et al.  Reservoir computing with a single time-delay autonomous Boolean node , 2014, Physical review. E, Statistical, nonlinear, and soft matter physics.

[16]  Lorenzo Livi,et al.  Determination of the Edge of Criticality in Echo State Networks Through Fisher Information Maximization , 2018, IEEE Transactions on Neural Networks and Learning Systems.

[17]  John C. Rodgers,et al.  True random number generation using CMOS Boolean chaotic oscillator , 2015, Microelectron. J..

[18]  Daniel P. Lathrop,et al.  RF Signal Classification using Boolean Reservoir Computing on an FPGA , 2021, 2021 International Joint Conference on Neural Networks (IJCNN).

[19]  H. Komkov.  Reservoir Computing for Prediction of Beam Evolution in Particle Accelerators , 2019 .

[20]  Mantas Lukosevicius,et al.  A Practical Guide to Applying Echo State Networks , 2012, Neural Networks: Tricks of the Trade.

[21]  Michael Ghil,et al.  Boolean delay equations. II. Periodic and aperiodic solutions , 1985 .

[22]  Michael Ghil,et al.  Boolean difference equations. I - Formulation and dynamic behavior , 1984 .

[23]  Jan Danckaert,et al.  Delay-Based Reservoir Computing: Noise Effects in a Combined Analog and Digital Implementation , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[24]  Toshiyuki Yamane,et al.  Recent Advances in Physical Reservoir Computing: A Review , 2018, Neural Networks.

[25]  Zheng Gao,et al.  Boolean chaos. , 2009, Physical review. E, Statistical, nonlinear, and soft matter physics.