175 citations · 343 across the 24 of their papers we have counts for
5 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…
Overcoming device unreliability with continuous learning in a population coding based computing system
Alice Mizrahi, Julie Grollier, Damien Querlioz +1
The brain, which uses redundancy and continuous learning to overcome the unreliability of its components, provides a promising path to building computing systems that are robust to…
Resonate and Fire Neuron with Fixed Magnetic Skyrmions
Md. Ali Azam, Dhritiman Bhattacharya, Damien Querlioz +1
In the brain, the membrane potential of many neurons oscillates in a subthreshold damped fashion and fire when excited by an input frequency that nearly equals their eigen frequenc…