Oscillatory Neural Networks for Edge AI Computing
Corentin Delacour, Stefania Carapezzi, Madeleine Abernot, Gabriele Boschetto, Nadine Azémard, Jérémie Salles, Thierry Gil, Aida Todri‐Sanial
Abstract
In this paper, we showcase the innovative concept of implementing Oscillatory Neural Networks (ONNs) for neuromorphic computing with beyond-CMOS devices based on vanadium dioxide to mimic neurons and resistors to emulate synapses. We explore ONN technology potentials from device to analog circuit-level simulations. We report that ONN behaves like an associative memory and can implement energy-based models such as Hopfield Neural Networks on edge devices. Finally, as a proof of concept, a reconfigurable digital ONN is implemented on FPGA for pattern recognition tasks.
Topics & Concepts
Neuromorphic engineeringComputer scienceField-programmable gate arrayArtificial neural networkContent-addressable memoryComputer architectureCMOSCellular neural networkResistorMemristorOptical computingEdge computingEnhanced Data Rates for GSM EvolutionArtificial intelligenceElectronic engineeringComputer hardwareElectrical engineeringEngineeringVoltageAdvanced Memory and Neural ComputingNeural Networks and Reservoir ComputingNeural dynamics and brain function