Pseudopatterns and dual-network memory models: Advantages and shortcomings

The dual-network memory model is designed to be a neurobiologically plausible manner of avoiding catastrophic interference. We discuss a number of advantages of this model and potential clues that the model has provided in the areas of memory consolidation, category-specific deficits, anterograde and retrograde amnesia. We discuss a surprising result about how this class of models handles episodic (“snap-shot”) memory — namely, that they seem to be able to handle both episodic and abstract memory — and discuss two other promising areas of research involving these models.

[1]  H. Eichenbaum,et al.  Memory, amnesia, and the hippocampal system , 1993 .

[2]  Robert M. French,et al.  Could category-specific semantic deficits reflect differences in the distribution of features within a unified semantic memory? , 1998 .

[3]  L. Squire.  Memory and the hippocampus: a synthesis from findings with rats, monkeys, and humans. , 1992, Psychological review.

[4]  R. French.  Catastrophic forgetting in connectionist networks , 1999, Trends in Cognitive Sciences.

[5]  R. Traub,et al.  Neuronal Networks of the Hippocampus , 1991 .

[6]  S. Kaplan.  The Physiology of Thought , 1950 .

[7]  Michael McCloskey,et al.  Catastrophic Interference in Connectionist Networks: The Sequential Learning Problem , 1989 .

[8]  B. McNaughton,et al.  Hebb-Marr networks and the neurobiological representation of action in space. , 1990 .

[9]  B. McNaughton,et al.  Memory trace reactivation in hippocampal and neocortical neuronal ensembles , 2000, Current Opinion in Neurobiology.

[10]  B. McNaughton,et al.  Hippocampal synaptic enhancement and information storage within a distributed memory system , 1987, Trends in Neurosciences.

[11]  Robert M. French.  Selective memory loss in aphasics: An insight from pseudo-recurrent connectionist networks , 1997, NCPW.

[12]  James L. McClelland,et al.  Why there are complementary learning systems in the hippocampus and neocortex: insights from the successes and failures of connectionist models of learning and memory. , 1995, Psychological review.

[13]  Anthony V. Robins,et al.  Catastrophic Forgetting and the Pseudorehearsal Solution in Hopfield-type Networks , 1998, Connect. Sci..

[14]  R. Stickgold,et al.  Sleep: off-line memory reprocessing , 1998, Trends in Cognitive Sciences.

[15]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[16]  R. Vertes,et al.  The case against memory consolidation in REM sleep. , 2000, The Behavioral and brain sciences.

[17]  A. Kendon,et al.  Organization of behavior in face-to-face interaction , 1975 .

[18]  E. Rolls,et al.  Computational analysis of the role of the hippocampus in memory , 1994, Hippocampus.

[19]  R Ratcliff,et al.  Connectionist models of recognition memory: constraints imposed by learning and forgetting functions. , 1990, Psychological review.

[20]  Anthony V. Robins,et al.  Catastrophic Forgetting, Rehearsal and Pseudorehearsal , 1995, Connect. Sci..

[21]  Bernard Ans,et al.  Neural networks with a self-refreshing memory: Knowledge transfer in sequential learning tasks without catastrophic forgetting , 2000, Connect. Sci..

[22]  Robert M. French,et al.  Pseudo-recurrent Connectionist Networks: An Approach to the 'Sensitivity-Stability' Dilemma , 1997, Connect. Sci..

[23]  Anthony V. Robins,et al.  Consolidation in Neural Networks and in the Sleeping Brain , 1996, Connect. Sci..