A massively parallel architecture for a self-organizing neural pattern recognition machine

By Gail A. Carpenter, Stephen Grossberg. 1988

Subfields: Model Architectures, Neural Architecture Search & AutoML

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

In Neural Architecture Search & AutoML

Citations in the corpus

Continuous Coordination As a Realistic Scenario for Lifelong Learning (2021, background): “Balancing between learning from recent experiences while not forgetting the knowledge acquired from the past is a well-studied problem known as the stability-plasticity dilemma (Carpenter & Grossberg, 1987).”
Online Continual Learning in Image Classification: An Empirical Survey (2021, background): “A more complex and general viewpoint of CL is the stabilityplasticity dilemma [4, 5] where stability refers to the ability to preserve past knowledge and plasticity denotes the fast adaptation of new knowledge.”
Towards Continual Reinforcement Learning: A Review and Perspectives (2020, background): “The tension between prioritizing recent experiences and past experiences, also known as the stability-plasticity dilemma, is often encountered when training neural networks and has also been demonstrated in the human brain (Carpenter and Grossberg, 1987).”
Continual Learning with Adaptive Weights (CLAW) (2019, positive): “Equivalent tradeoffs to the one between adaptation and stability can be found in the literature since the work in (Carpenter & Grossberg, 1987), in which a balance was needed to resolve the stabilityplasticity dilemma, where the latter refers to the ability to rapidly adapt to new tasks.”
Adaptive resonance theory (1997, neutral): “Models of unsupervised learning include ART 1 (Carpenter and Grossberg, 1987) for binary input pattems and fuzzy ART (Carpenter, Grossberg, and Rosen, 1991) for analog input patterns.”
A neurobiological model of visual attention and invariant pattern recognition based on dynamic routing of information (1993, background): “Step 1 is trivial, whereas step 4 is a high-level problem beyond the scope of this article (cf. Carpenter and Grossberg, 1987; Mumford, 1992).”
White Rose Consortium ePrints Repository (unknown): “The ART network trains by taking a new instance vector as input, matching this against the classes currently covered by the network and if the new data does not match an existing class given by equation 17 where n is the input dimensionality and ρ is a user-speciﬁed parameter (vigilance threshold) t”
On the computational architecture of the neocortex (2004, methodology): “The "Adaptive Resonance Theory" of Carpenter-Grossberg (Carpenter and Grossberg 1987) Thus Carpenter and Grossberg's theory is summarized in Fig.”
CARTMAP: a neural network method for automated feature selection in financial time series forecasting (2012, background): “[7] and supervised ARTMAP neural networks [8, 9] exhibit fast, stable, and incremental learning.”
Structure-Adaptable Digital Neural Networks (1999, unknown): “FAST (Alpaydin 90 [6]) (Carpenter & Grossberg 90 [38]) (Carpenter & Grossberg 87 [35]) (Carpenter & Grossberg 87[36]) (Grossberg 76 [70,71])”
Merging information in speech recognition: Feedback is never necessary (2000, unknown): “This rule, following the suggestion of Carpenter and Grossberg (1987), prevents decision nodes from becoming active at all in the absence of bottom-up support, thus ensuring that phonemic decisions are never based on lexical information alone.”
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).”
SUSTAIN: a network model of category learning. (2004, methodology): “(11) Unsupervised recruitment in SUSTAIN bears a strong resemblance to recruitment in adaptive resonance theory, Clapper and Bower's (1991) qualitative model (Carpenter & Grossberg, 1987), and Hartigan's (1975) leader algorithm.”
Clustering of time series data - a survey (2005, methodology): “Two prominent methods of the neural network approach to clustering are competitive learning, including ART [18] and self-organizing feature maps [19].”