How does a brain build a cognitive code?

By Stephen Grossberg. 1980

How researchers see this paper

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

In Neuroscience

Citations in the corpus

Experience Replay for Continual Learning (2018, background): “The problem of catastrophic forgetting in neural networks has long been recognized [6], and it is known that rehearsing past data can be a satisfactory antidote for some purposes [4, 18].”
Lifelong Learning of Spatiotemporal Representations With Dual-Memory Recurrent Self-Organization (2018, background): “…for learning novel knowledge and stable for preventing the disruption of consolidated knowledge is known as the stabilityplasticity dilemma, which has been extensively studied for both computational and biological systems (e.g., Grossberg, 1980, 2007; Mermillod et al., 2013; Ditzler et al., 2015).”
Continual Learning by Modeling Intra-Class Variation (2022, background): “This problem is closely connected to the stability-plasticity dilemma (Ditzler et al., 2015; Grossberg, 1982; Grossberg et al., 2012) in biological systems, where a system should be plastic enough to absorb new knowledge and at the same time stable enough not to catastrophically forget previous…”
Consistency is the key to further mitigating catastrophic forgetting in continual learning (2022, background): “The stability-plasticity dilemma, the root cause of catastrophic forgetting, has been well studied in both biological and artificial neural networks (Mermillod et al., 2013; Grossberg, 1982).”
Data Mining of Determinants of Intrauterine Growth Retardation Revisited Using Novel Algorithms Generating Semantic Maps and Prototypical Discriminating Variable Profiles (2015, methodology): “The only constraint is that all the values of every weight matrix have to be linearly scaled into the same range (typically between -1 and +1), while Grossberg’ IAC can work only with static excitations and inhibitions; iv) Each ACS unit tries to learn its specific value of decay, during its interac”
Specificity and abstractness of VOT imitation (2011, background): “Other lessextreme, and linguistically more informed, exemplar-based models include Johnson (1997), Pierrehumbert (2001, 2002, 2006), and Coleman (2002).”
A neural theory of visual attention: bridging cognition and neurophysiology. (2005, methodology): “A winner-take-all (WTA) cluster of a general type proposed by Grossberg (1976, 1980) can be used.”
Hierarchical Error Representation: A Computational Model of Anterior Cingulate and Dorsolateral Prefrontal Cortex (2015, background): “effective learning rate of the model (through modulation of predictions and, consequently, error signals needed to drive learning) in conditions when errors are predictable, the HER model suggests that dlPFC may play a role in resolving the stability-plasticity dilemma (Grossberg, 1980) by decreasin”
Generative learning structures and processes for generalized connectionist networks (1993, background): “[4] Resolution of the stability-plasticity dilemma (Grossberg, 1980), so as to be able to modify internal representations in response to changes in its environment and the tasks to be performed with minimal interference with performance on previously learned tasks.”
Connectionist Learning Procedures (1989, background): “There are many other interesting procedures which have been omitted [24, 26, 34, 35, 47, 54, 94].”
A Cortical Mechanism for Triggering Top-Down Facilitation in Visual Object Recognition (2003, background): “Several previous theories have promoted the involvement of top-down analysis in cortical processing (Ullman, 1995; Kosslyn, 1994; Mumford, 1994; Grossberg, 1980).”
Figure-ground mechanisms provide structure for selective attention (2007, background): “The attention effects in our experiments might be interpreted as examples of 'biased competition', in which visual objects compete for neural representation and top-down attention can bias the competition in favor of one or the other objec”
Computing with a Canonical Neural Circuits Model with Pool Normalization and Modulating Feedback (2014, methodology): “Because of the stabilizing and self-adapting properties of normalization (Sperling, 1970; Grossberg, 1973, 1980, 1988; Lyu & Simoncelli, 2009), we include a stage of divisive normalization in our model that (at steady state) captures equation 2.2.”
Grandmother cells and localist representations: a review of current thinking (2017, background): “these networks to learn quickly without suffering forgetting – the stability-plasticity dilemma (Grossberg, 1980).”