Associative Memories Using Complex-Valued Hopfield Networks Based on Spin-Torque Oscillator Arrays

12/06/2021
by   Nitin Prasad, et al.
0

Simulations of complex-valued Hopfield networks based on spin-torque oscillators can recover phase-encoded images. Sequences of memristor-augmented inverters provide tunable delay elements that implement complex weights by phase shifting the oscillatory output of the oscillators. Pseudo-inverse training suffices to store at least 12 images in a set of 192 oscillators, representing 16×12 pixel images. The energy required to recover an image depends on the desired error level. For the oscillators and circuitry considered here, 5 approximately 5 μs and consume roughly 130 nJ. Simulations show that the network functions well when the resonant frequency of the oscillators can be tuned to have a fractional spread less than 10^-3, depending on the strength of the feedback.

READ FULL TEXT

page 6

page 7

research
06/26/2017

A Fully Quaternion-Valued Capon Beamformer Based on Crossed-Dipole Arrays

Quaternion models have been developed for both direction of arrival esti...
research
12/14/2022

Fully Complex-valued Fully Convolutional Multi-feature Fusion Network (FC2MFN) for Building Segmentation of InSAR images

Building segmentation in high-resolution InSAR images is a challenging t...
research
09/04/2019

Phase retrieval of complex and vector-valued functions

The phase retrieval problem in the classical setting is to reconstruct r...
research
02/25/2021

Quantitative approximation results for complex-valued neural networks

We show that complex-valued neural networks with the modReLU activation ...
research
08/30/2023

Octonion Phase Retrieval

Signal processing over hypercomplex numbers arises in many optical imagi...
research
05/10/2023

Pseudo-reversing and its application for multiscaling of manifold-valued data

The well-known Wiener's lemma is a valuable statement in harmonic analys...

Please sign up or login with your details

Forgot password? Click here to reset