STT-SNN: A Spin-Transfer-Torque Based Soft-Limiting Non-Linear Neuron for Low-Power Artificial Neural Networks

Fan, Deliang; Shim, Yong; Raghunathan, Anand; Roy, Kaushik

doi:10.1109/tnano.2015.2437902

Cited by 58 publications

(38 citation statements)

References 37 publications

(89 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[41] Such neurotransistor is capable of propagating signals as biological neurons, which is important for efficiently implementing multiple layer neural networks. [102,[104][105][106][107] As we can see, in most of these researches, the functions of soma, axon, and dendrites are combined into a simple integrate-and-fire neuron and realized at the device level. [41,96] In addition, both ferroelectric field-effect transistors (FeFETs) relying on ferroelectric polarization switching and MRAM devices relying on magnetization switching have also been employed to emulate biological neuron behaviors.…”

Section: Artificial Neuronsmentioning

confidence: 99%

“…[41,96] In addition, both ferroelectric field-effect transistors (FeFETs) relying on ferroelectric polarization switching and MRAM devices relying on magnetization switching have also been employed to emulate biological neuron behaviors. [102,[104][105][106][107] As we can see, in most of these researches, the functions of soma, axon, and dendrites are combined into a simple integrate-and-fire neuron and realized at the device level. However, each individual part of the neuron is worthy of studying and mimicking, so as to achieve more complex and modulative neuronal characteristics.…”

Section: Artificial Neuronsmentioning

confidence: 99%

See 1 more Smart Citation

Bridging Biological and Artificial Neural Networks with Emerging Neuromorphic Devices: Fundamentals, Progress, and Challenges

et al. 2019

View full text Add to dashboard Cite

As the research on artificial intelligence booms, there is broad interest in brain‐inspired computing using novel neuromorphic devices. The potential of various emerging materials and devices for neuromorphic computing has attracted extensive research efforts, leading to a large number of publications. Going forward, in order to better emulate the brain's functions, its relevant fundamentals, working mechanisms, and resultant behaviors need to be re‐visited, better understood, and connected to electronics. A systematic overview of biological and artificial neural systems is given, along with their related critical mechanisms. Recent progress in neuromorphic devices is reviewed and, more importantly, the existing challenges are highlighted to hopefully shed light on future research directions.

show abstract

Section: Artificial Neuronsmentioning

confidence: 99%

Section: Artificial Neuronsmentioning

confidence: 99%

Bridging Biological and Artificial Neural Networks with Emerging Neuromorphic Devices: Fundamentals, Progress, and Challenges

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Various nonvolatile devices have been proposed to implement the linear operations in a deep neural network, including resistive random access memories (RRAM) 10 , phase change memories (PCM) 11 , ferroelectric RAM 12,13 and ferromagnetic memristors 14,15,16 . All exhibit a nonlinear dependence of conductance on programming voltage that is specific to the materials and device structure.…”

mentioning

confidence: 99%

Magnetic Domain Wall Based Synaptic and Activation Function Generator for Neuromorphic Accelerators

et al. 2019

View full text Add to dashboard Cite

Magnetic domain walls are information tokens in both logic and memory devices, and hold particular interest in applications such as neuromorphic accelerators that combine logic in memory. Here, we show that devices based on the electrical manipulation of magnetic domain walls are capable of implementing linear, as well as programmable nonlinear, functions. Unlike other approaches, domain-wall-based devices are ideal for application to both synaptic weight generators and thresholding in deep neural networks. Prototype micrometer-size devices operate with 8 ns current pulses and the energy consumption required for weight modulation is ≤ 16 pJ. Both speed and energy consumption compare favorably to other synaptic nonvolatile devices, with the expected energy dissipation for scaled 20-nm-devices close to that of biological neurons. Deep neural networks 1, 2 mimic the synaptic and activation functionality of human neurons using repeated applications of linear filters interspersed by nonlinear decision functions. Among other applications, deep neural networks offer promising solutions to image 3 , speech 4 and video 5recognition. Training is performed using a backpropagation learning procedure 6 , with the filter weights updated continuously like synapses, until the calculated output matches the desired output.

show abstract

“…An MTJ, formed between a magnetically pinned FM layer and d3 is used to sense the magnetization of d3. The device can be also operated as a neuron with a non-step transfer function if the domain wall is programmed at intermediate positions in the "free" layer of the device since the device resistance varies with the domain wall position [5]. Such non-step transfer functions are attractive for complex pattern recognition tasks since more information can be encoded in the neuron's output.…”

Section: ) Unipolar Domain Wall Neuronmentioning

confidence: 99%

Prospects of efficient neural computing with arrays of magneto-metallic neurons and synapses

Sengupta

Yogendra

Fan

et al. 2016

2016 21st Asia and South Pacific Design Automation Conference (ASP-DAC)

Self Cite

View full text Add to dashboard Cite

Non-von Neumann computing models, like Artificial and Spiking Neural Networks, inspired from the functionalities of the human brain, would require devices that can offer a direct mapping to the underlying neuroscience mechanisms for energyefficient and compact hardware implementation. To that effect, spin-transfer torque phenomena in devices based on lateral spin valves, domain wall motion in magnets and magnetic tunnel junctions can potentially pave the way for spintronic neural computing systems, where spintronic neurons interfaced with spintronic synapses, can directly mimic biological neural and synaptic functionalities. We explore various device structures suitable for such non-Boolean functionalities and demonstrate the potential benefits of such neural computing based on arrays of magneto-metallic neurons and synapses.

show abstract

STT-SNN: A Spin-Transfer-Torque Based Soft-Limiting Non-Linear Neuron for Low-Power Artificial Neural Networks

Cited by 58 publications

References 37 publications

Bridging Biological and Artificial Neural Networks with Emerging Neuromorphic Devices: Fundamentals, Progress, and Challenges

Bridging Biological and Artificial Neural Networks with Emerging Neuromorphic Devices: Fundamentals, Progress, and Challenges

Magnetic Domain Wall Based Synaptic and Activation Function Generator for Neuromorphic Accelerators

Prospects of efficient neural computing with arrays of magneto-metallic neurons and synapses

Contact Info

Product

Resources

About