TY - JOUR
T1 - Gaussian synapses for probabilistic neural networks
AU - Sebastian, Amritanand
AU - Pannone, Andrew
AU - Subbulakshmi Radhakrishnan, Shiva
AU - Das, Saptarshi
N1 - Funding Information:
The authors would like to acknowledge the contribution of Joseph R Nasr, Harikrishnan Ravichandran, Harikrishnan Jayachandrakurup, and Sarbashis Das for their help in device fabrication. This work was partially supported through Grant Number FA9550–17–1–0018 from Air Force Office of Scientific Research (AFOSR) through the Young Investigator Program.
Publisher Copyright:
© 2019, The Author(s).
PY - 2019/12/1
Y1 - 2019/12/1
N2 - The recent decline in energy, size and complexity scaling of traditional von Neumann architecture has resurrected considerable interest in brain-inspired computing. Artificial neural networks (ANNs) based on emerging devices, such as memristors, achieve brain-like computing but lack energy-efficiency. Furthermore, slow learning, incremental adaptation, and false convergence are unresolved challenges for ANNs. In this article we, therefore, introduce Gaussian synapses based on heterostructures of atomically thin two-dimensional (2D) layered materials, namely molybdenum disulfide and black phosphorus field effect transistors (FETs), as a class of analog and probabilistic computational primitives for hardware implementation of statistical neural networks. We also demonstrate complete tunability of amplitude, mean and standard deviation of the Gaussian synapse via threshold engineering in dual gated molybdenum disulfide and black phosphorus FETs. Finally, we show simulation results for classification of brainwaves using Gaussian synapse based probabilistic neural networks.
AB - The recent decline in energy, size and complexity scaling of traditional von Neumann architecture has resurrected considerable interest in brain-inspired computing. Artificial neural networks (ANNs) based on emerging devices, such as memristors, achieve brain-like computing but lack energy-efficiency. Furthermore, slow learning, incremental adaptation, and false convergence are unresolved challenges for ANNs. In this article we, therefore, introduce Gaussian synapses based on heterostructures of atomically thin two-dimensional (2D) layered materials, namely molybdenum disulfide and black phosphorus field effect transistors (FETs), as a class of analog and probabilistic computational primitives for hardware implementation of statistical neural networks. We also demonstrate complete tunability of amplitude, mean and standard deviation of the Gaussian synapse via threshold engineering in dual gated molybdenum disulfide and black phosphorus FETs. Finally, we show simulation results for classification of brainwaves using Gaussian synapse based probabilistic neural networks.
UR - http://www.scopus.com/inward/record.url?scp=85072231047&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85072231047&partnerID=8YFLogxK
U2 - 10.1038/s41467-019-12035-6
DO - 10.1038/s41467-019-12035-6
M3 - Article
C2 - 31519885
AN - SCOPUS:85072231047
VL - 10
JO - Nature Communications
JF - Nature Communications
SN - 2041-1723
IS - 1
M1 - 4199
ER -