OCTAN: An On-Chip Training Algorithm for Memristive Neuromorphic Circuits

In this paper, we propose a hardware friendly On-Chip Training Algorithm for the memristive Neuromorphic circuits (OCTAN). Although the proposed algorithm has a simple hardware like that of the random weight change (RWC) algorithm, it is much more efficient in terms of convergence speed and accuracy. In this algorithm, weights of the circuit are updated individually by a small value and the effect of individual weight update is assessed. If the weight change causes an increase in the error of the network, the weight update is reversed by applying the same change in the reverse direction twice. The usefulness of the proposed algorithm is verified by training some neuromorphic circuits for different applications. Compared to RWC and stochastic least-mean-squares (SLMS) training algorithms, our proposed algorithm needs, on average, <inline-formula> <tex-math notation="LaTeX">$329\times $ </tex-math></inline-formula> fewer epochs to find the minimum error point. Moreover, the accuracy of the networks trained by OCTAN is, on average, about 46% higher than those of RWC and SLMS algorithms. Additionally, a hardware for OCTAN is presented. This hardware provides a speedup of <inline-formula> <tex-math notation="LaTeX">$172\times $ </tex-math></inline-formula> (<inline-formula> <tex-math notation="LaTeX">$61\times $ </tex-math></inline-formula>) compared to that of the RWC (SLMS) algorithm. Finally, the impact of PVT (process, voltage, and temperature) variations is studied on the proposed training hardware indicating an average training error increase of less than 3.27% in the presence of variations.

[1]  Héctor Pomares,et al.  mHealthDroid: A Novel Framework for Agile Development of Mobile Health Applications , 2014, IWAAL.

[2]  Yiran Chen,et al.  Vortex: Variation-aware training for memristor X-bar , 2015, 2015 52nd ACM/EDAC/IEEE Design Automation Conference (DAC).

[3]  Qing Wu,et al.  Efficient and self-adaptive in-situ learning in multilayer memristor neural networks , 2018, Nature Communications.

[4]  Wei Lu,et al.  Two-terminal resistive switches (memristors) for memory and logic applications , 2011, 16th Asia and South Pacific Design Automation Conference (ASP-DAC 2011).

[5]  Mahmoud Zangeneh.  Designing energy-efficient sub-threshold logic circuits using equalization and non-volatile memory circuits using memristors , 2015 .

[6]  Michal Strzelecki,et al.  Hybrid no-propagation learning for multilayer neural networks , 2018, Neurocomputing.

[7]  Leon O. Chua,et al.  A Circuit-Based Learning Architecture for Multilayer Neural Networks With Memristor Bridge Synapses , 2015, IEEE Transactions on Circuits and Systems I: Regular Papers.

[8]  Yutaka Maeda,et al.  A learning rule of neural networks via simultaneous perturbation and its hardware implementation , 1995, Neural Networks.

[9]  Chris Yakopcic,et al.  Ex-situ training of dense memristor crossbar for neuromorphic applications , 2015, Proceedings of the 2015 IEEE/ACM International Symposium on Nanoscale Architectures (NANOARCH´15).

[10]  T. G. Habetler,et al.  Identification and control of induction motor stator currents using fast on-line random training of a neural network , 1995, IAS '95. Conference Record of the 1995 IEEE Industry Applications Conference Thirtieth IAS Annual Meeting.

[11]  Dhireesha Kudithipudi,et al.  A stochastic learning algorithm for neuromemristive systems , 2014, 2014 27th IEEE International System-on-Chip Conference (SOCC).

[12]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[13]  Jin Liu,et al.  A CMOS feedforward neural-network chip with on-chip parallel learning for oscillation cancellation , 2002, IEEE Trans. Neural Networks.

[14]  Tayfun Gokmen,et al.  Training Deep Convolutional Neural Networks with Resistive Cross-Point Devices , 2017, Front. Neurosci..

[15]  Daniel Soudry,et al.  A fully analog memristor-based neural network with online gradient training , 2016, 2016 IEEE International Symposium on Circuits and Systems (ISCAS).

[16]  Behzad Ebrahimi,et al.  A near-threshold 7T SRAM cell with high write and read margins and low write time for sub-20 nm FinFET technologies , 2015, Integr..

[17]  Mohsen Imani,et al.  Estimation of joint probability density function of delay and leakage power with variable skewness , 2013, 2013 International Conference on Electronics, Computer and Computation (ICECCO).

[18]  Leon O. Chua,et al.  Everything You Wish to Know About Memristors but Are Afraid to Ask , 2015, Handbook of Memristor Networks.

[19]  Gert Cauwenberghs,et al.  A Fast Stochastic Error-Descent Algorithm for Supervised Learning and Optimization , 1992, NIPS.

[20]  R. Fisher.  THE USE OF MULTIPLE MEASUREMENTS IN TAXONOMIC PROBLEMS , 1936 .

[21]  Yu Wang,et al.  TIME: A training-in-memory architecture for memristor-based deep neural networks , 2017, 2017 54th ACM/EDAC/IEEE Design Automation Conference (DAC).

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

[23]  Lei Zhang,et al.  Neuromorphic accelerators: A comparison between neuroscience and machine-learning approaches , 2015, 2015 48th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO).

[24]  M. Kanehisa,et al.  A knowledge base for predicting protein localization sites in eukaryotic cells , 1992, Genomics.

[25]  Carver A. Mead,et al.  Neuromorphic electronic systems , 1990, Proc. IEEE.

[26]  Chris Yakopcic,et al.  Generalized Memristive Device SPICE Model and its Application in Circuit Design , 2013, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

[27]  Marwan A. Jabri,et al.  Weight perturbation: an optimal architecture and learning technique for analog VLSI feedforward and recurrent multilayer networks , 1992, IEEE Trans. Neural Networks.

[28]  K. Hirotsu,et al.  An analog neural network chip with random weight change learning algorithm , 1993, Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan).

[29]  Mehdi Kamal,et al.  PHAX: Physical Characteristics Aware Ex-Situ Training Framework for Inverter-Based Memristive Neuromorphic Circuits , 2018, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

[30]  Mehdi Kamal,et al.  An Ultra Low-Power Memristive Neuromorphic Circuit for Internet of Things Smart Sensors , 2018, IEEE Internet of Things Journal.

[31]  Mehdi Kamal,et al.  Robust neuromorphic computing in the presence of process variation , 2017, Design, Automation & Test in Europe Conference & Exhibition (DATE), 2017.

[32]  William Nick Street,et al.  Breast Cancer Diagnosis and Prognosis Via Linear Programming , 1995, Oper. Res..

[33]  Avinoam Kolodny,et al.  Memristor-Based Multilayer Neural Networks With Online Gradient Descent Training , 2015, IEEE Transactions on Neural Networks and Learning Systems.