New paper on Nature Communications: Neuromorphic dendritic architecture with RRAM for efficient temporal processing with delays

An article in Nature Communications published by the Institute of Neuroinformatic, UZH/ETH Zurich (Filippo Moro, Tristan Torchet, Yiğit Demirağ, Giacomo Indiveri and Melika Payvand) and CEA-LETI in France features DenRAM, the first hardware realization of spiking neural network with dendritic architecture. It utilizes memristive devices to implement both delay and weight parameters, enhancing low-power signal processing with reduced memory use.

by Stefanie Paul-Cavallier
Enlarged view: Melika Payvand
Melika Payvand is head of the Emerging Intelligent Substrates (EIS) Lab at the Institute of Neuroinformatics (Source: Yiğit Demirağ)

To the Article in Nature Communications: external pageDenRAM: neuromorphic dendritic architecture with RRAM for efficient temporal processing with delays

Learn more about the topic in the podcast: external pageHow Memristors Will Help Machines Think at Different Timescales

Congratulations!

 

 

JavaScript has been disabled in your browser