Abstract
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.
Highlights
The recent decline in energy, size and complexity scaling of traditional von Neumann architecture has resurrected considerable interest in brain-inspired computing
Complexity scaling is on decline owing to the non-scalability of traditional von Neumann computing architecture and the impending “Dark Silicon” era that presents a severe threat to multi-core processor technology[9]
We reintroduce probabilistic neural networks (PNNs) that was proposed by Specht, D
Summary
The recent decline in energy, size and complexity scaling of traditional von Neumann architecture has resurrected considerable interest in brain-inspired computing. Slow learning, incremental adaptation, and false convergence are unresolved challenges for ANNs. In this article we, 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 experimentally demonstrate how a new class of analog devices, namely, Gaussian synapses, based on the heterostructure of novel atomically thin two dimensional (2D) layered semiconductors enables the hardware implementations of probabilistic neural networks (PNNs) and thereby reinstates all three aforementioned quintessential scaling aspects of computing. These new developments can facilitate Exascale Computing and benefit scientific discovery, national security, energy security, economic security, infrastructure development, and advanced healthcare programs[21,22]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
