English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Neuromorphic networks of artificial neurons and synapses can solvecomputational hard problems with energy efficiencies unattainable for vonNeumann architectures. For image processing, silicon neuromorphic processorsoutperform graphic processing units (GPUs) in energy efficiency by a largemargin, but they deliver much lower chip-scale throughput. Theperformance-efficiency dilemma for silicon processors may not be overcome byMoore's law scaling of complementary metal-oxide-semiconductor (CMOS)field-effect transistors. Scalable and biomimetic active memristor neurons andpassive memristor synapses form a self-sufficient basis for a transistorlessneural network. However, previous demonstrations of memristor neurons onlyshowed simple integrate-and-fire (I&F) behaviors and did not reveal the richdynamics and computational complexity of biological neurons. Here we show thatneurons built with nanoscale vanadium dioxide active memristors possess allthree classes of excitability and most of the known biological neuronaldynamics, and are intrinsically stochastic. With the favorable size and powerscaling, there is a path toward an all-memristor neuromorphic corticalcomputer.

Biological plausibility and stochasticity in scalable VO2 active memristor neurons