Deep Neural Networks using a Single Neuron: Folded-in-Time Architecture using Feedback-Modulated Delay Loops

TL;DR

This paper introduces Folded-in-time DNN (Fit-DNN), a novel approach that encodes deep neural networks within a single neuron using feedback loops, enabling dynamic temporal processing and potential hardware efficiency.

Contribution

It presents a method to implement deep neural networks as a single neuron with feedback loops, unifying network structure and dynamics in a novel temporal framework.

Findings

Successfully represents standard and sparse DNNs

Demonstrates promising benchmark performance

Enables DNN implementation with a single neuron

Abstract

Deep neural networks are among the most widely applied machine learning tools showing outstanding performance in a broad range of tasks. We present a method for folding a deep neural network of arbitrary size into a single neuron with multiple time-delayed feedback loops. This single-neuron deep neural network comprises only a single nonlinearity and appropriately adjusted modulations of the feedback signals. The network states emerge in time as a temporal unfolding of the neuron's dynamics. By adjusting the feedback-modulation within the loops, we adapt the network's connection weights. These connection weights are determined via a back-propagation algorithm, where both the delay-induced and local network connections must be taken into account. Our approach can fully represent standard Deep Neural Networks (DNN), encompasses sparse DNNs, and extends the DNN concept toward dynamical systems implementations. The new method, which we call Folded-in-time DNN (Fit-DNN), exhibits promising performance in a set of benchmark tasks.