DeepART: Deep Gradient-free Local Learning With Adaptive Resonance

Abstract

This article presents DeepART, a gradient-free and one-shot incremental learning technique for the training of deep Hebbian neural networks using the dynamics of Adaptive Resonance Theory (ART) algorithms. In the presented model, layers of a deep neural network are interpreted as modified FuzzyART modules with complement coded inputs and winner-take-all local weight updates with a FuzzyARTMAP head module providing feature-category-label mapping to enable supervised learning. These local weight update rules are derived for fully-connected and convolutional layers. DeepART provides a performance boost, reduction of category proliferation, and subsequently improved scalability to comparable ART-based methods for processing high-dimensional datasets in lifelong learning scenarios, combining the nonlinear feature representation learning of deep neural networks with the one-shot and lifelong learning properties of ART algorithms.

Department(s)

Electrical and Computer Engineering

Second Department

Computer Science

Comments

Missouri University of Science and Technology, Grant W911NF-22-2-0209

Keywords and Phrases

Adaptive resonance theory; Deep Hebbian learning; Lifelong machine learning; Task-incremental learning

International Standard Serial Number (ISSN)

1879-2782; 0893-6080

Document Type

Article - Journal

Document Version

Citation

File Type

text

Language(s)

English

Rights

© 2025 Elsevier, All rights reserved.

Publication Date

01 Oct 2025

Link to Full Text

Share

 
COinS