Learning without gradient descent encoded by the dynamics of a neurobiological model

03/16/2021
by   Vivek Kurien George, et al.
8

The success of state-of-the-art machine learning is essentially all based on different variations of gradient descent algorithms that minimize some version of a cost or loss function. A fundamental limitation, however, is the need to train these systems in either supervised or unsupervised ways by exposing them to typically large numbers of training examples. Here, we introduce a fundamentally novel conceptual approach to machine learning that takes advantage of a neurobiologically derived model of dynamic signaling, constrained by the geometric structure of a network. We show that MNIST images can be uniquely encoded and classified by the dynamics of geometric networks with nearly state-of-the-art accuracy in an unsupervised way, and without the need for any training.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

07/10/2020

Learning Unstable Dynamical Systems with Time-Weighted Logarithmic Loss

When training the parameters of a linear dynamical model, the gradient d...
08/15/2020

Correspondence between neuroevolution and gradient descent

We show analytically that training a neural network by stochastic mutati...
01/07/2021

A Comprehensive Study on Optimization Strategies for Gradient Descent In Deep Learning

One of the most important parts of Artificial Neural Networks is minimiz...
11/26/2019

Emergent Structures and Lifetime Structure Evolution in Artificial Neural Networks

Motivated by the flexibility of biological neural networks whose connect...
06/04/2021

Fluctuation-dissipation Type Theorem in Stochastic Linear Learning

The fluctuation-dissipation theorem (FDT) is a simple yet powerful conse...
05/15/2021

Gradient Descent in Materio

Deep learning, a multi-layered neural network approach inspired by the b...
11/18/2020

Gradient Starvation: A Learning Proclivity in Neural Networks

We identify and formalize a fundamental gradient descent phenomenon resu...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.