Neuromorphic Computing Enabled by Spin-Transfer Torque Devices

Neuromorphic computing offers immense possibilities in the development of self-learning, fault-tolerant, adaptive cognitive systems. However, the computing models are in complete contrast to the present sequential von-Neumann model of computation. Even custom analog/digital CMOS implementations of neural networks have been unable to achieve the ultra-low power and compact computing abilities of the human brain. In this tutorial, we review some of the neuromorphic computing models and demonstrate the manner in which spin-transfer torque effects in emerging spintronic devices can offer a direct mapping to such underlying neural computations.

[1]  Kaushik Roy,et al.  Spin-Orbit Torque Induced Spike-Timing Dependent Plasticity , 2014, ArXiv.

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

[3]  Charles H. Bennett,et al.  The thermodynamics of computation—a review , 1982 .

[4]  Kaushik Roy,et al.  AxNN: Energy-efficient neuromorphic systems using approximate computing , 2014, 2014 IEEE/ACM International Symposium on Low Power Electronics and Design (ISLPED).

[5]  Kaushik Roy,et al.  Spin Neurons: A Possible Path to Energy-Efficient Neuromorphic Computers , 2013, ArXiv.

[6]  G. Bi,et al.  Synaptic modification by correlated activity: Hebb's postulate revisited. , 2001, Annual review of neuroscience.

[7]  K. Roy,et al.  Spin-Based Neuron Model With Domain-Wall Magnets as Synapse , 2012, IEEE Transactions on Nanotechnology.

[8]  Andrew S. Cassidy,et al.  A million spiking-neuron integrated circuit with a scalable communication network and interface , 2014, Science.

[9]  Kaushik Roy,et al.  Spin-Transfer Torque Magnetic neuron for low power neuromorphic computing , 2015, 2015 International Joint Conference on Neural Networks (IJCNN).

[10]  Zhengya Zhang,et al.  A Sparse Coding Neural Network ASIC With On-Chip Learning for Feature Extraction and Encoding , 2015, IEEE Journal of Solid-State Circuits.

[11]  Kaushik Roy,et al.  Spin Orbit Torque Based Electronic Neuron , 2014, ArXiv.

[12]  Mrigank Sharad,et al.  Energy-Efficient Non-Boolean Computing With Spin Neurons and Resistive Memory , 2014, IEEE Transactions on Nanotechnology.

[13]  Matthew Cook,et al.  Unsupervised learning of digit recognition using spike-timing-dependent plasticity , 2015, Front. Comput. Neurosci..

[14]  Kaushik Roy,et al.  SPINDLE: SPINtronic Deep Learning Engine for large-scale neuromorphic computing , 2014, 2014 IEEE/ACM International Symposium on Low Power Electronics and Design (ISLPED).

[15]  Kaushik Roy,et al.  STT-SNN: A Spin-Transfer-Torque Based Soft-Limiting Non-Linear Neuron for Low-Power Artificial Neural Networks , 2014, IEEE Transactions on Nanotechnology.

[16]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[17]  Hojjat Adeli,et al.  Spiking Neural Networks , 2009, Int. J. Neural Syst..