Energy efficient spiking neural network design with RRAM devices

The brain-inspired neural networks have demonstrated great potential in big data analysis. The spiking neural network (SNN), which encodes the real world data into spike trains, promises great performance in computational ability and energy efficiency. Moreover, it is much more biologically plausible than the traditional artificial neural network (ANN), which keeps the input data in its original form. In this paper, we introduce an RRAM-based energy efficient implementation of STDP-based spiking neural network cascaded with ANN classifier. The recognition accuracy and power consumption are compared between SNN and traditional three-layer ANN. The experiments on the MNIST database demonstrate that the proposed RRAM-based spiking neural network requires only 14% of power consumption compared with RRAM-based artificial neural network with a slight accuracy decay (~2%).

[1]  Cong Xu,et al.  Design of cross-point metal-oxide ReRAM emphasizing reliability and cost , 2013, 2013 IEEE/ACM International Conference on Computer-Aided Design (ICCAD).

[2]  Wolfgang Maass,et al.  Networks of Spiking Neurons: The Third Generation of Neural Network Models , 1996, Electron. Colloquium Comput. Complex..

[3]  2014 International Symposium on Integrated Circuits (ISIC), Singapore, December 10-12, 2014 , 2014, ISIC.

[4]  Jacques-Olivier Klein,et al.  Bioinspired networks with nanoscale memristive devices that combine the unsupervised and supervised learning approaches , 2012, 2012 IEEE/ACM International Symposium on Nanoscale Architectures (NANOARCH).

[5]  Sally A. McKee,et al.  Hitting the memory wall: implications of the obvious , 1995, CARN.

[6]  Peter Dayan,et al.  Theoretical Neuroscience: Computational and Mathematical Modeling of Neural Systems , 2001 .

[7]  K. Doya,et al.  Memorizing oscillatory patterns in the analog neuron network , 1989, International 1989 Joint Conference on Neural Networks.

[8]  Qing Wu,et al.  Hardware realization of BSB recall function using memristor crossbar arrays , 2012, DAC Design Automation Conference 2012.

[9]  Timothée Masquelier,et al.  Unsupervised Learning of Visual Features through Spike Timing Dependent Plasticity , 2007, PLoS Comput. Biol..

[10]  L. Abbott,et al.  Competitive Hebbian learning through spike-timing-dependent synaptic plasticity , 2000, Nature Neuroscience.

[11]  Shimeng Yu,et al.  Stochastic learning in oxide binary synaptic device for neuromorphic computing , 2013, Front. Neurosci..

[12]  Eugene M. Izhikevich,et al.  Which model to use for cortical spiking neurons? , 2004, IEEE Transactions on Neural Networks.

[13]  Jeffrey Bokor,et al.  Extremely scaled silicon nano-CMOS devices , 2003, Proc. IEEE.

[14]  Giacomo Indiveri,et al.  A low-power adaptive integrate-and-fire neuron circuit , 2003, Proceedings of the 2003 International Symposium on Circuits and Systems, 2003. ISCAS '03..

[15]  Byoungil Lee,et al.  Nanoelectronic programmable synapses based on phase change materials for brain-inspired computing. , 2012, Nano letters.

[16]  J Joshua Yang,et al.  Memristive devices for computing. , 2013, Nature nanotechnology.