656 citations · 2.1k across the 27 of their papers we have counts for
3 papers · 1 filter
Use of Magnetoresistive Random-Access Memory as Approximate Memory for Training Neural Networks
Nicolas Locatelli, Adrien F. Vincent, Damien Querlioz
Hardware neural networks that implement synaptic weights with embedded non-volatile memory, such as spin torque memory (ST-MRAM), are a major lead for low energy artificial intelli…
Nano-oscillator-based classification with a machine learning-compatible architecture
Damir Vodenicarevic, Nicolas Locatelli, Julie Grollier +1
Pattern classification architectures leveraging the physics of coupled nano-oscillators have been demonstrated as promising alternative computing approaches, but lack effective lea…
Circuit-Level Evaluation of the Generation of Truly Random Bits with Superparamagnetic Tunnel Junctions
Damir Vodenicarevic, Nicolas Locatelli, Alice Mizrahi +4
Many emerging alternative models of computation require massive numbers of random bits, but their generation at low energy is currently a challenge. The superparamagnetic tunnel ju…