Convolutional Networks for Image Processing by Coupled Oscillator Arrays

2014/09/15 by Dmitri E. Nikonov, Nikonov, Dmitri E., Ian A. Young +3 · 1 citation
Computer Science · Engineering · Neuroscience · #Advanced Memory and Neural Computing #Computer Vision and Pattern Recognition (cs.CV) #Disordered Systems and Neural Networks (cond-mat.dis-nn) #FOS: Computer and information sciences #FOS: Physical sciences #Neural Networks and Reservoir Computing #Neural dynamics and brain function #Pattern Formation and Solitons (nlin.PS)

paper · pdf · doi:10.48550/arxiv.1409.4469

openalex publication_date 2014/09/15 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

A coupled oscillator array is shown to approximate convolutions with Gabor filters for image processing tasks. Pixelated image fragments and filter functions are converted to voltages, differenced, and input into a corresponding array of weakly coupled Voltage Controlled Oscillators (VCOs). This is referred to as Frequency Shift Keying (FSK). Upon synchronization of the array, the common node amplitude provides a metric for the degree of match between the image fragment and the filter function. The optimal oscillator parameters for synchronization are determined and favor a moderate value of the Q-factor.

Citations

• Gradient-based learning applied to document recognition
• Neuromorphic electronic systems

Cited by

• X-Band Fin Resonant Body Transistors in 14nm CMOS Technology

Related

• Convolution Inference via Synchronization of a Coupled CMOS Oscillator Array
• Coupled VO2 oscillators circuit as analog first layer filter in convolutional neural networks
• A Coupled CMOS Oscillator Array for 8ns and 55pJ Inference in Convolutional Neural Networks
• Training and synchronizing oscillator networks with Equilibrium Propagation
• A Frequency Domain Neural Network for Fast Image Super-resolution