Energy-efficient spiking neural networks based on Tunnel FET

Tunnel FETs (TFETs) with steep switching slope have emerged as an attractive device for energy-efficient circuit implementations. In this work, we explore Spiking Neural Network (SNN) based on Tunnel FETs. Neuron and binary image edge detection circuits implemented using 22 nm predictive technology-based bulk MOSFET models and 20 nm Verilog-A-based table model GaSb-InAs heterojunction TFETs are studied. TFET-based implementation is seen to provide better performance at lower power consumption regime, while the MOSFET-based edge detection circuit produces superior performance at higher power regime.

[1]  Giacomo Indiveri,et al.  A VLSI array of low-power spiking neurons and bistable synapses with spike-timing dependent plasticity , 2006, IEEE Transactions on Neural Networks.

[2]  Dharmendra S. Modha,et al.  A digital neurosynaptic core using embedded crossbar memory with 45pJ per spike in 45nm , 2011, 2011 IEEE Custom Integrated Circuits Conference (CICC).

[3]  Suman Datta,et al.  Application of Silicon-Germanium Source Tunnel-FET to Enable Ultralow Power Cellular Neural Network-Based Associative Memory , 2014, IEEE Transactions on Electron Devices.

[4]  Saibal Mukhopadhyay,et al.  Exploring Tunnel-FET for ultra low power analog applications: A case study on operational transconductance amplifier , 2013, 2013 50th ACM/EDAC/IEEE Design Automation Conference (DAC).

[5]  Giacomo Indiveri,et al.  A VLSI neuromorphic device for implementing spike-based neural networks , 2011, WIRN.

[6]  Vinay Saripalli,et al.  III-V Tunnel FET Model , 2015 .

[7]  Chiara Bartolozzi,et al.  Synaptic Dynamics in Analog VLSI , 2007, Neural Computation.

[8]  Gert Cauwenberghs,et al.  Neuromorphic Silicon Neuron Circuits , 2011, Front. Neurosci.

[9]  A. Seabaugh,et al.  Tunnel Field-Effect Transistors: State-of-the-Art , 2014, IEEE Journal of the Electron Devices Society.

[10]  P. Hasler,et al.  A bio-physically inspired silicon neuron , 2004 .

[11]  Wei Zhao.  Predictive technology modeling for scaled CMOS , 2009 .

[12]  Bernard Brezzo,et al.  TrueNorth: Design and Tool Flow of a 65 mW 1 Million Neuron Programmable Neurosynaptic Chip , 2015, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

[13]  Wilhelm Burger,et al.  Digital Image Processing - An Algorithmic Introduction using Java , 2008, Texts in Computer Science.

[14]  Adrian M. Ionescu,et al.  Tunnel field-effect transistors as energy-efficient electronic switches , 2011, Nature.