Gaussian Synapses for Probabilistic Neural Networks

This 11-page article, from Nature Communications, discusses probabilistic neural networks (PNNs) that can improve computing power through energy scaling, size scaling, and complexity scaling. The authors highlight how 2D materials enable aggressive size scaling, analog Gaussian synapses support energy-efficient computation, and PNNs drive complexity scaling. Combined, these developments can facilitate exascale computing and ultimately benefit scientific discovery, national security, energy security, economic security, infrastructure development, and advanced healthcare programs." Other topics covered in this article include brainwave patterns, device fabrication and measurements, and EEG data.