Litcius/Paper detail

Convolution Inference via Synchronization of a Coupled CMOS Oscillator Array

Dmitri E. Nikonov, Peter Kurahashi, James Ayers, Hai Li, Telesphor Kamgaing, Georgios C. Dogiamis, Hyung‐Jin Lee, Y. Fan, Ian A. Young

2020IEEE Journal on Exploratory Solid-State Computational Devices and Circuits37 citationsDOIOpen Access PDF

Abstract

Oscillator neural networks (ONNs) are a promising hardware option for artificial intelligence. With an abundance of theoretical treatments of ONNs, few experimental implementations exist to date. In contrast to prior publications of only building block functionality, we report a practical experimental demonstration of neural computing using an ONN. The arrays contain 26 CMOS ring oscillators in the GHz range of frequencies are tuned by image data and convolution kernels. Synchronization of oscillators results in an analog output voltage approximating convolution neural network operation.

Topics & Concepts

Convolution (computer science)CMOSComputer scienceSynchronization (alternating current)Artificial neural networkInferenceElectronic engineeringRange (aeronautics)Ring oscillatorBlock (permutation group theory)VoltageAlgorithmArtificial intelligenceMathematicsElectrical engineeringEngineeringTelecommunicationsAerospace engineeringGeometryChannel (broadcasting)Neural Networks and Reservoir ComputingAdvanced Memory and Neural ComputingNeural dynamics and brain function
Convolution Inference via Synchronization of a Coupled CMOS Oscillator Array | Litcius