Adaptive resonance theory

By Stephen Grossberg. 1997

SyNAPSE program of the Defense Advanced Projects Research Agency (Hewlett-Packard Company, subcontract under DARPA prime contract HR0011-09-3-0001, and HRL Laboratories LLC, subcontract #801881-BS under DARPA prime contract HR0011-09-C-0001); CELEST, an NSF Science of Learning Center (SBE-0354378)

Subfields: Model Architectures

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Model Architectures

Citations in the corpus

Continual Lifelong Learning with Neural Networks: A Review (2018, background): “Plasticity plays a crucial role in the emergence of sensorimotor behaviour by complementing genetic information which provides a specific evolutionary path (Grossberg, 2012).”
Continuous Learning in Single-Incremental-Task Scenarios (2018, background): “During the past few years we have witnessed a renewed and growing attention to Continuous Learning (CL) [3][4][25].”
Generative Negative Text Replay for Continual Vision-Language Pretraining (2022, background): “Traditional continual learning methods mostly focus on the issue of stabilityplasticity dilemma [18,45], where a model is prone to forgetting the previously learned knowledge when adapting to new data.”
Online Continual Learning with Contrastive Vision Transformer (2022, background): “Continual learning requires neural networks to be both stable to prevent forgetting as well as plastic to learn new concepts, which is referred to as the stability-plasticity dilemma [55,27].”
DER: Dynamically Expandable Representation for Class Incremental Learning (2021, background): “In particular, it requires a model to effectively incorporate novel concepts without forgetting the existing knowledge, which is also known as stability-plasticity dilemma [9].”
Incremental learning algorithms and applications (2016, methodology): “This is at the core of popular incremental models such as ART networks [77, 56], or meta-strategies to deal with concept drift such as the just-in-time classifier JIT [3], or hybrid online/offline methods [120, 43].”
Unsupervised Machine Learning for Networking: Techniques, Applications and Research Challenges (2017, background): “ons and (bottom-up) sensory information while keeping their difference within the threshold limits of vigilance parameter, which in result is considered as the member of the expected class of neurons [45]. Learning of an ART model primarily consists of a comparison ﬁeld, recognition ﬁeld, vigilance ”