Self-refreshing memory in artificial neural networks: learning temporal sequences without catastrophic forgetting

References

• Altmann , GTM . 2002 . Learning and development in neural networks—the importance of prior experience . Cognition , 85 : 43 – 50 .
   PubMed Web of Science ®Google Scholar
• Altmann , GTM and Dienes , Z . 1999 . Rule learning by seven-month-old infants and neural networks . Science , 284 : 875
   Google Scholar
• Ans , B . 1990 . Neuromimetic model for storage and recall of temporal sequences . CR Académie des Sciences Paris, Life Sciences , 311 : 7 – 12 .
   PubMed Web of Science ®Google Scholar
• Ans , B , Carbonnel , S and Valdois , S . 1998 . A connectionist multiple-trace memory model for polysyllabic word reading . Psychological Review , 105 : 678 – 723 .
   PubMed Web of Science ®Google Scholar
• Ans , B , Coiton , Y , Gilhodes , JC and Velay , JL . 1994 . A neural network model for temporal sequence learning and motor programming . Neural Networks , 7 : 1461 – 1476 .
   Web of Science ®Google Scholar
• Ans , B and Rousset , S . 1997 . Avoiding catastrophic forgetting by coupling two reverberating neural networks . CR Académie des Sciences Paris, Life Sciences , 320 : 989 – 997 .
   Web of Science ®Google Scholar
• Ans , B and Rousset , S . 2000 . Neural networks with a self-refreshing memory: knowledge transfer in sequential learning tasks without catastrophic forgetting . Connection Science , 12 : 1 – 19 .
   Web of Science ®Google Scholar
• Ans B Rousset S French RM Musca S 2002 Preventing catastrophic interference in multiple-sequence learning using coupled reverberating Elman networks In Proceedings of the 24th Annual Conference of the Cognitive Science Society Hillsdale NJ Lawrence Erlbaum pp. 71–76
   Google Scholar
• Baddeley AD Hitch G 1974 Working memory In G. A. Bower (ed.) Recent Advances in Learning and Motivation 8 New York Academic Press
   Google Scholar
• Barnes , J and Underwood , B . 1959 . ‘Fate’ of first-list associations in transfer theory . Journal of Experimental Psychology , 58 : 97 – 105 .
   PubMedGoogle Scholar
• Botvinick , M and Plaut , DC . 2004 . Doing without schema hierarchies: a recurrent connectionist approach to normal and impaired routine sequential action . Psychological Review , 111 : 395 – 429 .
   PubMed Web of Science ®Google Scholar
• Carpenter , GA and Grossberg , S . 1988 . The ART of adaptive pattern recognition by a self-organizing neural network . Computer , 21 : 77 – 88 .
   Web of Science ®Google Scholar
• Cleeremans A 1993 Mechanisms of Implicit Learning: Connectionist Models of Sequence Processing Cambridge MA MIT Press
   Google Scholar
• Cleeremans A Destrebecqz A 1997 Incremental sequence learning In Proceedings of the 19th Annual Conference of the Cognitive Science Society Hillsdale NJ Lawrence Erlbaum pp. 119–124
   Google Scholar
• Cohen , A , Ivry , R and Keele , SW . 1990 . Attention and structure in sequence learning . Journal of Experimental Psychology: Learning, Memory, and Cognition , 16 : 17 – 30 .
   Web of Science ®Google Scholar
• Destrebecqz , A and Cleeremans , A . 2001 . Can sequence learning be implicit? New evidence with the process dissociation procedure . Psychonomic Bulletin and Review , 8 : 343 – 350 .
   PubMed Web of Science ®Google Scholar
• Dienes , Z , Altmann , GTM and Gao , SJ . 1999 . Mapping across domains without feedback: a neural network model of transfer of implicit knowledge . Cognitive Science , 23 : 53 – 82 .
   Web of Science ®Google Scholar
• Elman , JL . 1990 . Finding structure in time . Cognitive Science , 14 : 179 – 211 .
   Web of Science ®Google Scholar
• French , RM . 1992 . Semi-distributed representations and catastrophic forgetting in connectionist networks . Connection Science , 4 : 365 – 377 .
   Google Scholar
• French RM 1994 Dynamically constraining connectionist networks to produce distributed, orthogonal representations to reduce catastrophic interference In Proceedings of the 16th Annual Conference of the Cognitive Science Society Hillsdale NJ Lawrence Erlbaum pp. 335–340
   Google Scholar
• French , RM . 1997 . Pseudo-recurrent connectionist networks: an approach to the ‘sensitivity–stability’ dilemma . Connection Science , 9 : 353 – 379 .
   Google Scholar
• French , RM . 1999 . Catastrophic forgetting in connectionist networks . Trends in Cognitive Sciences , 3 : 128 – 135 .
   PubMed Web of Science ®Google Scholar
• French RM Ans B Rousset S 2001 Pseudopatterns and dual-network memory models: advantages and shortcomings In R. French and J. Sougné (eds) Connectionist Models of Learning, Development and Evolution London Springer pp. 1–10
   Google Scholar
• Grossberg , S . 1987 . Competitive learning: from interactive activation to adaptive resonance . Cognitive Science , 11 : 23 – 63 .
   Web of Science ®Google Scholar
• Hanson , SJ and Negishi , M . 2002 . On the emergence of rules in neural networks . Neural Computation , 14 : 2245 – 2268 .
   PubMed Web of Science ®Google Scholar
• Hebb DO 1949 The Organization of Behavior New York Wiley
   Google Scholar
• Hetherington P Seidenberg M 1989 Is there ‘catastrophic interference’ in connectionist networks? In Proceedings of the 11th Annual Conference of the Cognitive Science Society Hillsdale NJ Lawrence Erlbaum pp. 26–33
   Google Scholar
• Hinton , GE . 1989a . Connectionist learning procedures . Artificial Intelligence , 40 : 185 – 234 .
   Web of Science ®Google Scholar
• Hinton , GE . 1989b . Deterministic Boltzmann learning performs steepest descent in weight-space . Neural Computation , 1 : 143 – 150 .
   Web of Science ®Google Scholar
• Hintzman , DL . 1986 . ‘Schema abstraction’ in a multiple-trace memory model . Psychological Review , 93 : 411 – 428 .
   Web of Science ®Google Scholar
• Jordan MI 1986 Serial Order: A Parallel Distributed Processing Approach Technical Report ICS-8604 University of California at San Diego CA
   Google Scholar
• Kanerva P 1988 Sparse Distributed Memory Cambridge MA MIT Press
   Google Scholar
• Kortge CA 1990 Episodic memory in connectionist networks In Proceedings of the 12th Annual Conference of the Cognitive Science Society Hillsdale NJ Lawrence Erlbaum pp. 764–771
   Google Scholar
• Kruschke , JK . 1992 . ALCOVE: an exemplar-based connectionist model of category learning . Psychological Review , 99 : 22 – 44 .
   PubMed Web of Science ®Google Scholar
• Kruschke , JK . 1993 . Human category learning: implications for backpropagation models . Connection Science , 5 : 3 – 36 .
   Google Scholar
• Lewandowsky S 1991 Gradual unlearning and catastrophic interference: a comparison of distributed architectures In W. E. Hockley and S. Lewandowsky (eds) Relating Theory and Data: Essays on Human Memory in Honor of Bennet B. Murdock Hillsdale NJ Lawrence Erlbaum pp. 445–476
   Google Scholar
• Lewandowsky , S . 1994 . On the relation between catastrophic interference and generalization in connectionist networks . Journal of Biological Systems , 2 : 307 – 333 .
   Google Scholar
• Lewandowsky S Li SC 1995 Catastrophic interference in neural networks. Causes, solutions, and data In F. N. Dempster and C. Brainerd (eds) New Perspectives on Interference and Inhibition in Cognition New York Academic Press pp. 329–361
   Google Scholar
• Maquet , P , Laureys , S , Peigneux , P , Fuchs , S , Petiau , C , Phillips , C , Aerts , J , Del Fiore , G , Degueldre , C , Meulemans , T , Luxen , A , Franck , G , Van Der Linden , M , Smith , C and Cleeremans , A . 2000 . Experience-dependent changes in cerebral activation during human REM sleep . Nature Neuroscience , 3 : 831 – 836 .
   PubMed Web of Science ®Google Scholar
• Maskara A Noetzel A 1992 Forced simple recurrent neural network and grammatical inference In Proceedings of the 14th Annual Conference of the Cognitive Science Society Hillsdale NJ Lawrence Erlbaum pp. 420–425
   Google Scholar
• Maskara , A and Noetzel , A . 1993 . Sequence learning with recurrent neural networks . Connection Science , 5 : 139 – 152 .
   Google Scholar
• McClelland , JL , McNaughton , BL and O'Reilly , RC . 1995 . Why there are complementary learning systems in the hippocampus and neocortex: insights from the successes and failures of connectionist models of learning and memory . Psychological Review , 102 : 419 – 457 .
   PubMed Web of Science ®Google Scholar
• McCloskey M Cohen NJ 1989 Catastrophic interference in connectionist networks: the sequential learning problem In G. H. Bower (ed.) The Psychology of Learning and Motivation 24 New York Academic Press pp. 109–165
   Google Scholar
• McRae K Hetherington PA 1993 Catastrophic interference is eliminated in pretrained networks In Proceedings of the 15th Annual Conference of the Cognitive Science Society Hillsdale NJ Lawrence Erlbaum pp. 723–728
   Google Scholar
• Murre JMJ 1992 The effects of pattern presentation on interference in backpropagation networks In Proceedings of the 14th Annual Conference of the Cognitive Science Society Hillsdale NJ Lawrence Erlbaum pp. 54–59
   Google Scholar
• O'Reilly , RC . 1996 . Biologically plausible error-driven learning using local activation differences: the generalized recirculation algorithm . Neural Computation , 8 : 895 – 938 .
   Web of Science ®Google Scholar
• Page , M . 2000 . Connectionist modelling in psychology: a localist manifesto . Behavioral and Brain Sciences , 23 : 443 – 467 .
   PubMed Web of Science ®Google Scholar
• Peterson , C and Anderson , J . 1987 . A mean field theory learning algorithm for neural networks . Complex Systems , 1 : 995 – 1019 .
   Google Scholar
• Plaut , DC , McClelland , JL , Seidenberg , MS and Patterson , K . 1996 . Understanding normal and impaired word reading: computational principles in quasi-regular domains . Psychological Review , 103 : 56 – 115 .
   PubMed Web of Science ®Google Scholar
• Ratcliff , R . 1990 . Connectionist models of recognition memory: constraints imposed by learning and forgetting functions . Psychological Review , 97 : 285 – 308 .
   PubMed Web of Science ®Google Scholar
• Reber , AS . 1967 . Implicit learning of artificial grammars . Journal of Verbal Learning and Verbal Behaviour , 6 : 855 – 863 .
   Google Scholar
• Reed , J and Johnson , P . 1994 . Assessing implicit learning with indirect tests: determining what is learned about sequence structure . Journal of Experimental Psychology: Learning, Memory, and Cognition , 20 : 585 – 594 .
   Web of Science ®Google Scholar
• Reiss , M and Taylor , JG . 1991 . Storing temporal sequences . Neural Networks , 4 : 773 – 787 .
   Web of Science ®Google Scholar
• Robins , AV . 1995 . Catastrophic forgetting, rehearsal and pseudorehearsal . Connection Science , 7 : 123 – 146 .
   Google Scholar
• Robins , AV . 1996 . Consolidation in neural networks and in the sleeping brain . Connection Science , 8 : 259 – 275 .
   Google Scholar
• Robins , AV and McCallum , S . 1998 . Catastrophic forgetting and the pseudorehearsal solution in Hopfield-type networks . Connection Science , 10 : 121 – 135 .
   Web of Science ®Google Scholar
• Robins , AV and McCallum , S . 1999 . The consolidation of learning during sleep: comparing the pseudorehearsal and unlearning accounts . Neural Networks , 12 : 1191 – 1206 .
   PubMed Web of Science ®Google Scholar
• Shanks , DR and Johnstone , T . 1999 . Evaluating the relationship between explicit and implicit knowledge in a sequential reaction time task . Journal of Experimental Psychology: Learning, Memory, and Cognition , 25 : 1435 – 1451 .
   PubMed Web of Science ®Google Scholar
• Sharkey , NE and Sharkey , AJC . 1995 . An analysis of catastrophic interference . Connection Science , 7 : 301 – 329 .
   Google Scholar
• Xie , X and Seung , HS . 2003 . Equivalence of backpropagation and contrastive Hebbian learning in a layered network . Neural Computation , 15 : 441 – 454 .
   PubMed Web of Science ®Google Scholar