Catastrophic Interference in Connectionist Networks: The Sequential Learning Problem

McCloskey, Michael; Cohen, Neal J.

doi:10.1016/s0079-7421(08)60536-8

Cited by 2,804 publications

(2,008 citation statements)

References 7 publications

Supporting

Mentioning

1,844

Contrasting

Unclassified

Order By: Relevance

“…As these associations were unrelated to the original ones, the weight changes they induced had the same effect on the original associations as adding random noise to the weights. Thus, performance on the original task was significantly impaired as a result of the interference training (also see McCloskey & Cohen, 1989;Ratcliff, 1990). The network was then retrained on only half of the original 100 associations.…”

Section: Hinton and Plaut (1987)mentioning

confidence: 99%

Relearning after Damage in Connectionist Networks: Toward a Theory of Rehabilitation

1996

View full text Add to dashboard Cite

Connectionist modeling offers a useful computational framework for exploring the nature of normal and impaired cognitive processes. The current work extends the relevance of connectionist modeling in neuropsychology to address issues in cognitive rehabilitation: the degree and speed of recovery through retraining, the extent to which improvement on treated items generalizes to untreated items, and how treated items are selected to maximize this generalization. A network previously used to model impairments in mapping orthography to semantics is retrained after damage. The degree of relearning and generalization varies considerably for different lesion locations, and has interesting implications for understanding the nature and variability of recovery in patients. In a second simulation, retraining on words whose semantics are atypical of their category yields more generalization than retraining on more typical words, suggesting a counterintuitive strategy for selecting items in patient therapy to maximize recovery. In a final simulation, changes in the pattern of errors produced by the network over the course of recovery is used to constrain explanations of the nature of recovery of analogous braindamaged patients. Taken together, the findings demonstrate that the nature of relearning in damaged connectionist networks can make important contributions to a theory of rehabilitation in patients.

show abstract

Section: Hinton and Plaut (1987)mentioning

confidence: 99%

Relearning after Damage in Connectionist Networks: Toward a Theory of Rehabilitation

1996

View full text Add to dashboard Cite

show abstract

“…He also notes, quite correctly, that many advances being made in connectionism are the result of attempting to account for cognitive phenomena, not the result of attempts to provide more realistic neural models. For example, the introduction of modularity into networks (Nowlan, 1990, Jacobs et al, 1991 is partly the result of attempts to overcome catastrophic interference (McCloskey and Cohen, 1989). Thus, the overriding goal in connectionist modeling is not to characterize neural systems, but to develop a framework useful for describing cognitive performance.…”

Section: Applying the Alternative Conception Of Levels To Mental Phenmentioning

confidence: 99%

Levels of description and explanation in cognitive science

Bechtel

1994

Mind Mach

154

View full text Add to dashboard Cite

Abstract. The notion of levels has been widely used in discussions of cognitive science, especially in discussions of the relation of connectionism to symbolic modeling of cognition. I argue that many of the notions of levels employed are problematic for this purpose, and develop an alternative notion grounded in the framework of mechanistic explanation. By considering the source of the analogies underlying both symbolic modeling and connectionist modeling, I argue that neither is likely to provide an adequate analysis of processes at the level at which cognitive theories attempt to function: One is drawn from too low a level, the other from too high a level. If there is a distinctly cognitive level, then we still need to determine what are the basic organizational principles at that level.Key words. Connectionism, symbol processing, levels of organization, reduction, mechanistic explanation.The recent attention given to connectionist, parallel distributed processing, or neural network models of cognition has raised a fundamental question about how these inquiries relate to other attempts to explain cognitive phenomenon. The use of the three different names sometimes interchangeably and sometimes distinctively revels that there is a fair amount of disagreement as to how to answer this question. The name neural networks suggests that these are models of actual neural systems. For some theorists, this implies that these models are, at best, tangentially relevant to the business of cognitive science. They may be useful for studying how structures in the brain function, and since cognitive activities are realized in the brain, they may be relevant for studying how cognitive activities are realized in the brain, but that is all. Some neuroscientists, especially those who adopt the term cognitive neuroscience for their pursuit, however, would insist that neuroscience is in the business of explaining cognitive functions. Thus, there are some investigators who would employ the term neural networks who take themselves to be engaged in explaining cognitive functions. For many of these theorists it is important to develop models of how the brain performs cognitive functions, and they are therefore quite skeptical of the research programs commonly associated with the term cognitive science which have not made faithfulness to neural mechanism primary.Other theorists, who are more likely to have come to such network models by way of psychology or artificial intelligence, tend to prefer the labels connectionism or parallel distributed processing 2. This choice of names reflects a different conception of the enterprise. For these theorists, network models are attractive only in part because of their similarity to networks of neurons. The attraction is more due to the fact that such networks provide useful frameworks for modeling

show abstract

“…While repeating the same stimulus or sequence of stimuli may lead to similar synaptic changes for each repetition, processing different stimuli on each trial may reverse or overwrite these changes to a certain extent. Such interference effects are well-known in distributed neural network models of learning [39,41]. These effects would not necessarily interact with presentation rate because the changes depend on the stimulus processing that occurs with each trial rather than on time, per se.…”

Section: Perseveration and Cholinergic Deficitsmentioning

confidence: 98%

Mechanisms underlying perseveration in aphasia: evidence from a single case study

Gotts¹,

Rocchetta²,

Cipolotti³

2002

Neuropsychologia

View full text Add to dashboard Cite

Catastrophic Interference in Connectionist Networks: The Sequential Learning Problem

Cited by 2,804 publications

References 7 publications

Relearning after Damage in Connectionist Networks: Toward a Theory of Rehabilitation

Relearning after Damage in Connectionist Networks: Toward a Theory of Rehabilitation

Levels of description and explanation in cognitive science

Mechanisms underlying perseveration in aphasia: evidence from a single case study

Contact Info

Product

Resources

About