Analog neuron with s-domain characteristic

An analog element for use as a neuron in a recurrent neural network is described, the analog element having memory of a prior layer state and being a continuous time circuit rather than having a discrete clocking interval. The element is characterized and described by the Laplace s-domain operator,...

Full description

Saved in:
Bibliographic Details
Main Author Mallinson, A. Martin
Format Patent
LanguageEnglish
Published 25.10.2022
Subjects
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
PHYSICS
Online AccessGet full text

Cover

More Information
Summary:An analog element for use as a neuron in a recurrent neural network is described, the analog element having memory of a prior layer state and being a continuous time circuit rather than having a discrete clocking interval. The element is characterized and described by the Laplace s-domain operator, as distinct from a digital solution that uses the z-domain operator appropriate for quantized time descriptions. Rather than using an all-pass filter, the analog equivalent of a unit delay in the z-domain, a finite gain integrator, which is a simpler circuit, may be used to provide the delay in the analog s-domain. The resulting circuit may be easily implemented at the transistor level.
Bibliography:Application Number: US202016806980