ART 2: self-organization of stable category recognition codes for analog input patterns.

By Gail A. Carpenter, Stephen Grossberg. 1987

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

Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges (2019, background): “This phenomenon is known to be a common problem for multitask learning, and is also related to the stability vs plasticity dilemma (Carpenter and Grossberg, 1987; Gross-berg, 1988).”
Uncertainty-based Continual Learning with Adaptive Regularization (2019, background): “The main challenge is to resolve the so-called stability-plasticity dilemma [2, 18].”
Tag-Trigger-Consolidation: A Model of Early and Late Long-Term-Potentiation and Depression (2008, background): “memories need to be protected against overwriting by completely different memory items [19], a model based on tagging would have an intrinsic vigilance threshold via the trigger threshold Np.”
ARTMAP: supervised real-time learning and classification of nonstationary data by a self-organizing neural network (1991, methodology): “A more complete discussion of this aspect of ART 1 system design is given by Carpenter and Grossberg (1987a).”
Information Theoretic Clustering (2002, methodology): “For instance, merging and splitting, neighborhood dependent, hierarchical methods, and ART networks [12], [18], [6], [7].”
Survey of clustering algorithms (2005, unknown): “Use crossover (two-point crossover) and mutation (bit-wise mutation) operator to generate offspring from the individuals chosen in step 2).”
Neural networks in geophysical applications (2000, methodology): “These include the self-organizing map of Kohonen (1989), the adaptive resonance theory of Carpenter and Grossberg (1987), and the Hopfield network (Hopfield, 1984) and other recurrent”
Adaptive Group Sparse Regularization for Continual Learning (2020, background): “However, there is a fundamental tradeoff that needs to be overcome: the stabilityplasticity dilemma [5, 20].”
Striking a Balance between Stability and Plasticity for Class-Incremental Learning (2021, unknown): “This is a stability-plasticity dilemma [3, 14] – on the one hand, our model should learn more new knowledge for the sake of plasticity, while on the other hand, our model needs to maintain more old knowledge for the sake of stability (without catastrophic forgetting [27, 31]).”
Mathematical formulations of Hebbian learning (2002, background): “Grossberg has coined the term ‘stability-plasticity dilemma’ for this problem [Grossberg, 1987, Carpenter and Grossberg, 1987].”
Clustering: A neural network approach (2010, unknown): “In Carpenter and Grossberg (1987b), F2 initially contains a number of uncommitted nodes, which get committed one by one upon the input presentation.”
Approaches for automated detection and classification of masses in mammograms (2006, unknown): “The unsupervised model was based on an adaptive resonance theory (ART2) network [172,173] and the supervised model was based on LDA.”
Early lexical development in a self-organizing neural network (2004, methodology): “To solve this problem, our model implements GMAPs by a novel combination of SOM with the Adaptive Resonance Theory for real-valued patterns (model ART2; Carpenter & Grossberg, 1987).”