Spin neuron for ultra low power computational hardware

Sharad, Mrigank; Panagopoulos, Georgios; Roy, Kaushik

doi:10.1109/drc.2012.6257039

Cited by 24 publications

(26 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Application of device structures based on lateral spin valves [9,11], as well as domain-wall magnets (DWM) [10,12] were proposed. [14,16,17,18].…”

Section: Spin Torque Neuronmentioning

confidence: 99%

“…However, such schemes may not lead to scalable and energy-efficient designs. We proposed the application of ultra-low-voltage, current-mode spin-torque switches as neurons in our recent work [9][10][11][12].. In this work we present the basic rationale of using nano-scale spin-torque switches as 'neurons' for the design of highly energy-efficient neural-networks [10].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Spin-neurons: A possible path to energy-efficient neuromorphic computers

Sharad

Fan

Roy

2013

Journal of Applied Physics

Self Cite

View full text Add to dashboard Cite

Recent years have witnessed growing interest in the field of brain-inspired computing based on neural-network architectures. In order to translate the related algorithmic models into powerful, yet energy-efficient cognitive-computing hardware, computing-devices beyond CMOS may need to be explored. The suitability of such devices to this field of computing would strongly depend upon how closely their physical characteristics match with the essential computing primitives employed in such models. In this work we discuss the rationale of applying emerging spin-torque devices for bio-inspired computing. Recent spin-torque experiments have shown the path to low-current, low-voltage and high-speed magnetization switching in nano-scale magnetic devices. Such magneto-metallic, current-mode spin-torque switches can mimic the analog summing and 'thresholding' operation of an artificial neuron with high energy-efficiency.Comparison with CMOS-based analog circuit-model of neuron shows that spin neurons can achieve more than two orders of magnitude lower energy and beyond three orders of magnitude reduction in energy-delay product. The application of spin neurons can therefore be an attractive option for neuromorphic computers of future.2

show abstract

“…Application of device structures based on lateral spin valves [9,11], as well as domain-wall magnets (DWM) [10,12] were proposed. [14,16,17,18].…”

Section: Spin Torque Neuronmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Spin-neurons: A possible path to energy-efficient neuromorphic computers

Sharad

Fan

Roy

2013

Journal of Applied Physics

Self Cite

View full text Add to dashboard Cite

show abstract

“…Such magneto-metallic devices can operate at ultra-low terminal voltages and can implement current-mode summation and comparison operations at ultra-low energy cost. Such current-mode spin switches or 'neurons' can be exploited in energy efficient analog-mode computing [28,34,35]. In this work we present the design of RCN based energy-efficient computing blocks for HTM using such 'spin neurons'.…”

Section: Hierarchical Temporal Memory Based On Spin-neurons and Resismentioning

confidence: 99%

“…A winner take all (WTA) circuit should be attached to the RCN based pattern matching network. The DWN device essentially acts as a low-voltage, high-speed, high-resolution current-mode comparator and hence can be exploited in digitizing analog current levels at ultra-low energy cost [28]. The proposed WTA scheme, algorithmically depicted in fig.…”

Section: B Winner Take All Designmentioning

confidence: 99%