Abstract
This chapter provides with an overview of the motivation and direction for neuro-memristive computing hardware. The emergence of deep learning technologies has been largely attributed to the convergence in the growth on computational capabilities, and that of the large availability of the data resulting from Internet of things applications. The need to have higher computational capabilities enforces the need to have low power solutions and smaller devices. However, the physical limits of CMOS device and process technologies pushed us in the recent years to think beyond CMOS era computing. A promising solutions is a class of emerging devices called memristors, that can naturally blend as a viable computing device to implement neural computations that extend the capabilities of exiting computing hardware. The full potential of neuro-memristive systems is yet to be completely realised and could provide ways to develop higher level of socially engineered machine cognition.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Agrawal A, Roy K (2019) Mimicking leaky-integrate-fire spiking neuron using automotion of domain walls for energy-efficient brain-inspired computing. IEEE Trans Magn 55(1):1–7
Akinaga H, Shima H (2010) Resistive random access memory (reram) based on metal oxides. Proc IEEE 98(12):2237–2251
Amit DJ, Amit DJ (1992) Modeling brain function: the world of attractor neural networks. Cambridge University Press, Cambridge
Bourzac K (2017) Has intel created a universal memory technology?[news]. IEEE Spectr 54(5):9–10
Chua L (2018) Five non-volatile memristor enigmas solved. Appl Phys A 124(8):563
Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A, Bengio Y (2014) Generative adversarial nets. In: Advances in neural information processing systems, pp 2672–2680
Goodfellow I, Bengio Y, Courville A, Bengio Y (2016) Deep learning, vol 1. MIT Press, Cambridge
Grandison T, Sloman M (2000) A survey of trust in internet applications. IEEE Commun Surv Tutor 3(4):2–16
Guo X, Ipek E, Soyata T (2010) Resistive computation: avoiding the power wall with low-leakage, STT-MRAM based computing. In: ACM SIGARCH computer architecture news, vol 38. ACM, pp 371–382
Hurst S (1969) An introduction to threshold logic: a survey of present theory and practice. Radio Electron Eng 37(6):339–351
Jeong H, Shi L (2018) Memristor devices for neural networks. J Phys D: Appl Phys 52(2):023003
Krestinskaya O, Dolzhikova I, James AP (2018) Hierarchical temporal memory using memristor networks: a survey. IEEE Trans Emerg Top Comput Intell 2(5):380–395. https://doi.org/10.1109/TETCI.2018.2838124
Krestinskaya O, James AP, Chua LO (2019) Neuro-memristive circuits for edge computing: a review. IEEE Trans Neural Networks Learn Syst (https://doi.org/10.1109/TNNLS.2019.2899262). arXiv:1807.00962
Krestinskaya O, Salama KN, James AP (2018) Learning in memristive neural network architectures using analog backpropagation circuits. IEEE Trans Circuits Syst I: Regul Pap 1–14. https://doi.org/10.1109/TCSI.2018.2866510
Krestinskaya O, Bakambekova A, James AP (2019) Amsnet: analog memristive system architecture for mean-pooling with dropout convolutional neural network. In: IEEE international conference on artificial intelligence circuits and systems
Li Y, Wang Z, Midya R, Xia Q, Yang JJ (2018) Review of memristor devices in neuromorphic computing: materials sciences and device challenges. J Phys D: Appl Phys 51(50):503002
Liao Q, Poggio T (2016) Bridging the gaps between residual learning, recurrent neural networks and visual cortex. arXiv:1604.03640
Lippmann R (1987) An introduction to computing with neural nets. IEEE ASSP Mag 4(2):4–22
Ma J, Tang J (2017) A review for dynamics in neuron and neuronal network. Nonlinear Dyn 89(3):1569–1578
Maan AK, Jayadevi DA, James AP (2017) A survey of memristive threshold logic circuits. IEEE Trans Neural Netw Learn Syst 28(8):1734–1746
McCulloch WS, Pitts W (1943) A logical calculus of the ideas immanent in nervous activity. Bull Math Biophys 5(4):115–133
Medsker L, Jain LC (1999) Recurrent neural networks: design and applications. CRC Press, Boca Raton
Mhaskar H, Liao Q, Poggio T (2016) Learning functions: when is deep better than shallow. arXiv:1603.00988
Nili H, Adam GC, Hoskins B, Prezioso M, Kim J, Mahmoodi MR, Bayat FM, Kavehei O, Strukov DB (2018) Hardware-intrinsic security primitives enabled by analogue state and nonlinear conductance variations in integrated memristors. Nat Electron 1(3):197
Raghu M, Poole B, Kleinberg J, Ganguli S, Dickstein JS (2017) On the expressive power of deep neural networks. In: Proceedings of the 34th international conference on machine learning-volume 70. pp 2847–2854. https://www.JMLR.org
Rajendran J, Rose GS, Karri R, Potkonjak M (2012) Nano-ppuf: a memristor-based security primitive. In: IEEE computer society annual symposium on VLSI (ISVLSI). IEEE, pp 84–87
Schlkopf B, Smola AJ, Bach F (2018) Learning with kernels: support vector machines, regularization, optimization, and beyond
Schmidhuber J (2015) Deep learning in neural networks: an overview. Neural Netw 61:85–117
Serrano-Gotarredona T, Masquelier T, Prodromakis T, Indiveri G, Linares-Barranco B (2013) STDP and STDP variations with memristors for spiking neuromorphic learning systems. Front Neurosci 7:2
Sicari S, Rizzardi A, Grieco LA, Coen-Porisini A (2015) Security, privacy and trust in internet of things: the road ahead. Comput Netw 76:146–164
Smagulova K, Krestinskaya O, James AP (2018) A memristor-based long short term memory circuit. Analog Integr Circuits Signal Process 95(3):467–472
Talati N, Ha H, Perach B, Ronen R, Kvatinsky S (2019) Concept: a column oriented memory controller for efficient memory and PIM operations in RRAM. IEEE Micro
Ujfalussy BB, Makara JK, Branco T, Lengyel M (2015) Dendritic nonlinearities are tuned for efficient spike-based computations in cortical circuits. Elife 4:e10056
Varga A, Moore R (1990) Hidden Markov model decomposition of speech and noise. In: 1990 International conference on acoustics, speech, and signal processing, ICASSP-90. IEEE, pp 845–848
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Chapter Highlights
Chapter Highlights
-
Generalization and expressive power of deep neural networks outweigh the simplicity of shallow neural networks.
-
The crossbar memristive arrays function as a dot product operator useful for performing weight summation of inputs in a neural network layer.
-
Implementations of memristor based neural computing is area and power efficient, and provides the possibility to perform analog computations of large scale neural networks on chip.
-
The stability of memristor devices, process reliability and maturity for industrial manufacturing, packaging issues and accuracy of very large scale circuit simulations will be the key factors for the success of neuro-memristive chips.
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this chapter
Cite this chapter
James, A.P. (2020). Introduction to Neuro-Memristive Systems. In: James, A. (eds) Deep Learning Classifiers with Memristive Networks. Modeling and Optimization in Science and Technologies, vol 14. Springer, Cham. https://doi.org/10.1007/978-3-030-14524-8_1
Download citation
DOI: https://doi.org/10.1007/978-3-030-14524-8_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-14522-4
Online ISBN: 978-3-030-14524-8
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)