In plain words: Tiny memory cells in a grid store each brain-like synapse's strength as electrical resistance, so algorithms can run on brain-inspired chips; this report surveys them. It mainly covers turning ordinary deep neural networks into spiking ones, which fire only when needed and so save power.

Abstract · RRAM based neuromorphic algorithms

This submission is a report on RRAM based neuromorphic algorithms. This report basically gives an overview of the algorithms implemented on neuromorphic hardware with crossbar array of RRAM synapses. This report mainly talks about the work on deep neural network to spiking neural network conversion and its significance.

Roshan Gopalakrishnan
arXiv:1903.02519 · q-bio.NC, cs.ET, cs.NE · submitted Jan 12, 2019
abstract · pdf · html · 12 pages, 6 figures, A version of this survey report is submitting as Springer book chapter