Connectionist models of recognition memory: constraints imposed by learning and forgetting functions.

Multilayer connectionist models of memory based on the encoder model using the backpropagation learning rule are evaluated. The models are applied to standard recognition memory procedures in which items are studied sequentially and then tested for retention. Sequential learning in these models leads to 2 major problems. First, well-learned information is forgotten rapidly as new information is learned. Second, discrimination between studied items and new items either decreases or is nonmonotonic as a function of learning. To address these problems, manipulations of the network within the multilayer model and several variants of the multilayer model were examined, including a model with prelearned memory and a context model, but none solved the problems. The problems discussed provide limitations on connectionist models applied to human memory and in tasks where information to be learned is not all available during learning.

[1]  B. Underwood,et al.  Fate of first-list associations in transfer theory. , 1959, Journal of experimental psychology.

[2]  Richard C. Atkinson,et al.  Human Memory: A Proposed System and its Control Processes , 1968, Psychology of Learning and Motivation.

[3]  R. Atkinson,et al.  Rehearsal processes in free recall: A procedure for direct observation , 1970 .

[4]  John R. Anderson,et al.  RECOGNITION AND RETRIEVAL PROCESSES IN FREE RECALL , 1972 .

[5]  James A. Anderson,et al.  A simple neural network generating an interactive memory , 1972 .

[6]  James A. Anderson,et al.  A theory for the recognition of items from short memorized lists , 1973 .

[7]  Stephen A. Ritz,et al.  Distinctive features, categorical perception, and probability learning: some applications of a neural model , 1977 .

[8]  Teuvo Kohonen,et al.  Associative memory. A system-theoretical approach , 1977 .

[9]  Roger Ratcliff,et al.  A Theory of Memory Retrieval. , 1978 .

[10]  S. Grossberg.  How does a brain build a cognitive code , 1980 .

[11]  J. Eich.  A composite holographic associative recall model. , 1982 .

[12]  B. Murdock.  A Theory for the Storage and Retrieval of Item and Associative Information. , 1982 .

[13]  Bennet B. Murdock,et al.  A distributed memory model for serial-order information. , 1983 .

[14]  J.A. Anderson,et al.  Theory of categorization based on distributed memory storage. , 1984 .

[15]  R. Shiffrin,et al.  A retrieval model for both recognition and recall. , 1984, Psychological review.

[16]  Ray Pike,et al.  Comparison of convolution and matrix distributed memory systems for associative recall and recognition , 1984 .

[17]  Ray Pike,et al.  Comparison of convolution and matrix distributed memory systems for associative recall and recognition. , 1984 .

[18]  Geoffrey E. Hinton,et al.  A Learning Algorithm for Boltzmann Machines , 1985, Cogn. Sci..

[19]  James L. McClelland,et al.  Distributed memory and the representation of general and specific information. , 1985, Journal of experimental psychology. General.

[20]  J. Eich.  Levels of processing, encoding specificity, elaboration, and CHARM. , 1985, Psychological review.

[21]  Douglas L. Hintzman,et al.  "Schema Abstraction" in a Multiple-Trace Memory Model , 1986 .

[22]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[23]  James L. McClelland,et al.  James L. McClelland, David Rumelhart and the PDP Research Group, Parallel distributed processing: explorations in the microstructure of cognition . Vol. 1. Foundations . Vol. 2. Psychological and biological models . Cambridge MA: M.I.T. Press, 1987. , 1989, Journal of Child Language.

[24]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[25]  Stephen Grossberg,et al.  Competitive Learning: From Interactive Activation to Adaptive Resonance , 1987, Cogn. Sci..

[26]  B Kosko,et al.  Adaptive bidirectional associative memories. , 1987, Applied optics.

[27]  Stephen Grossberg,et al.  A massively parallel architecture for a self-organizing neural pattern recognition machine , 1988, Comput. Vis. Graph. Image Process..

[28]  Douglas L. Hintzman,et al.  Judgments of frequency and recognition memory in a multiple-trace memory model. , 1988 .

[29]  R. Ratcliff,et al.  A retrieval theory of priming in memory. , 1988, Psychological review.

[30]  Stephen Grossberg,et al.  Nonlinear neural networks: Principles, mechanisms, and architectures , 1988, Neural Networks.

[31]  B. Murdock,et al.  The replacement effect: Repeating some items while replacing others , 1988, Memory & cognition.

[32]  R Ratcliff,et al.  Continuous versus discrete information processing modeling accumulation of partial information. , 1988, Psychological review.

[33]  Murdock,et al.  Learning in a distributed memory model. , 1989 .

[34]  James L. McClelland,et al.  A distributed, developmental model of word recognition and naming. , 1989, Psychological review.

[35]  Geoffrey E. Hinton,et al.  Parallel Models of Associative Memory , 1989 .

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

[37]  R. Shiffrin,et al.  List-strength effect: I. Data and discussion. , 1990, Journal of experimental psychology. Learning, memory, and cognition.

[38]  R. Shiffrin,et al.  List-strength effect: I. Data and discussion. , 1990 .

[39]  R. Shiffrin,et al.  List-strength Effect: Ii. Theoretical Mechanisms , 1990 .