Adaptive Resonance

Adaptive Resonance Theory (ART) is a neural network framework designed for online, unsupervised learning, primarily focusing on pattern recognition and clustering in dynamic environments. Current research emphasizes developing ART-based algorithms for continual learning, addressing challenges like parameter estimation and improving clustering performance in federated learning settings and many-objective optimization. These advancements are significant for applications requiring robust, adaptable systems capable of handling evolving data streams, such as robotics, anomaly detection, and personalized medicine.

Papers

September 7, 2023

Privacy-preserving Continual Federated Clustering via Adaptive Resonance Theory
Naoki Masuyama, Yusuke Nojima, Yuichiro Toda, Chu Kiong Loo, Hisao Ishibuchi, Naoyuki Kubota
Clustering Algorithm Clustering Performance Federated Clustering Adaptive Resonance

May 25, 2023

L1 Adaptive Resonance Ratio Control for Series Elastic Actuator with Guaranteed Transient Performance
Feiyan Min, Gao Wang, Xueqin Chen
Adaptive Control Series Elastic Actuator Elastic Actuator Adaptive Resonance Position Control

May 19, 2023

An Ensemble Semi-Supervised Adaptive Resonance Theory Model with Explanation Capability for Pattern Classification
Farhad Pourpanah, Chee Peng Lim, Ali Etemad, Q. M. Jonathan Wu
Semi Supervised Learning Pattern Recognition Explanation Capability Adaptive Resonance

May 1, 2023

A Parameter-free Adaptive Resonance Theory-based Topological Clustering Algorithm Capable of Continual Learning
Naoki Masuyama, Takanori Takebayashi, Yusuke Nojima, Chu Kiong Loo, Hisao Ishibuchi, Stefan Wermter
Continual LEArning State of the Art Clustering Topological Clustering Adaptive Resonance

March 3, 2023

The Grossberg Code: Universal Neural Network Signatures of Perceptual Experience
Birgitta Dresp-Langley
Code Data Universal Deep Contextual Modulation Adaptive Resonance

February 6, 2023

Intrinsic Rewards from Self-Organizing Feature Maps for Exploration in Reinforcement Learning
Marius Lindegaard, Hjalmar Jacob Vinje, Odin Aleksander Severinsen
Reinforcement Learning Environment Exploration Intrinsic Reward Self Organizing Map Adaptive Resonance

April 22, 2022

Reference Vector Adaptation and Mating Selection Strategy via Adaptive Resonance Theory-based Clustering for Many-objective Optimization
Takato Kinoshita, Naoki Masuyama, Yiping Liu, Yusuke Nojima, Hisao Ishibuchi
Evolutionary Algorithm Clustering Algorithm Many Objective Optimization Adaptive Resonance Decomposition Based Direct Mating

March 18, 2022

Class-wise Classifier Design Capable of Continual Learning using Adaptive Resonance Theory-based Topological Clustering
Naoki Masuyama, Yusuke Nojima, Farhan Dawood, Zongying Liu
Continual LEArning Free Learning Topological Clustering Adaptive Resonance

January 26, 2022

Adaptive Resonance Theory-based Topological Clustering with a Divisive Hierarchical Structure Capable of Continual Learning
Naoki Masuyama, Narito Amako, Yuna Yamada, Yusuke Nojima, Hisao Ishibuchi
Continual LEArning Hierarchical Structure State of the Art Clustering Topological Clustering Adaptive Resonance Divisive Hierarchical Clustering Algorithm

Adaptive Resonance

Papers

Privacy-preserving Continual Federated Clustering via Adaptive Resonance Theory

L1 Adaptive Resonance Ratio Control for Series Elastic Actuator with Guaranteed Transient Performance

An Ensemble Semi-Supervised Adaptive Resonance Theory Model with Explanation Capability for Pattern Classification

A Parameter-free Adaptive Resonance Theory-based Topological Clustering Algorithm Capable of Continual Learning

The Grossberg Code: Universal Neural Network Signatures of Perceptual Experience

Intrinsic Rewards from Self-Organizing Feature Maps for Exploration in Reinforcement Learning

Reference Vector Adaptation and Mating Selection Strategy via Adaptive Resonance Theory-based Clustering for Many-objective Optimization

Class-wise Classifier Design Capable of Continual Learning using Adaptive Resonance Theory-based Topological Clustering

Adaptive Resonance Theory-based Topological Clustering with a Divisive Hierarchical Structure Capable of Continual Learning