Connectionist models of recognition memory: Constraints imposed by learning and forgetting functions.
Abstract
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.
Cites (36)
- Learning Internal Representations by Error PropagationRumelhart, David E., Hinton, Geoffrey E., Williams, Ronald J. · 1985
- Human Memory: A Proposed System and its Control ProcessesAtkinson, R.C., Shiffrin, R.M. · 1968 · Psychology of Learning and Motivation
- A theory of memory retrieval.Ratcliff, Roger · 1978 · Psychological Review
- A distributed, developmental model of word recognition and naming.Seidenberg, Mark S., McClelland, James L. · 1989 · Psychological Review
- Catastrophic Interference in Connectionist Networks: The Sequential Learning ProblemMcCloskey, Michael, Cohen, Neal J. · 1989 · Psychology of Learning and Motivation
- A learning algorithm for Boltzmann machinesAckley, David H., Hinton, Geoffrey E., Sejnowski, Terrence J. · 1985 · Cognitive Science
- A massively parallel architecture for a self-organizing neural pattern recognition machineCarpenter, Gail A., Grossberg, Stephen · 1987 · Computer Vision, Graphics, and Image Processing
- "Schema abstraction" in a multiple-trace memory model.Hintzman, Douglas L. · 1986 · Psychological Review
- Nonlinear neural networks: Principles, mechanisms, and architecturesGrossberg, Stephen · 1988 · Neural Networks
- A retrieval model for both recognition and recall.Gillund, Gary, Shiffrin, Richard M. · 1984 · Psychological Review
Cited by (942)
- Overcoming catastrophic forgetting in neural networksKirkpatrick, James, Pascanu, Razvan, Rabinowitz, Neil, Veness, Joel, Desjardins, Guillaume, Rusu, Andrei A., Milan, Kieran, Quan, John, Ramalho, Tiago, Grabska-Barwinska, Agnieszka et al. · 2017 · Proceedings of the National Academy of Sciences
- Why there are complementary learning systems in the hippocampus and neocortex: insights from the successes and failures of connectionist models of learning and memoryMcClelland, James L., McNaughton, Bruce L., O'Reilly, Randall C. · 1995 · Psychological Review
- Catastrophic Interference in Connectionist Networks: The Sequential Learning ProblemMcCloskey, Michael, Cohen, Neal J. · 1989 · Psychology of Learning and Motivation
- Continual lifelong learning with neural networks: A reviewParisi, German I., Kemker, Ronald, Part, Jose L., Kanan, Christopher, Wermter, Stefan · 2019 · Neural Networks
- On the Opportunities and Risks of Foundation ModelsBommasani, Rishi, Hudson, Drew A., Adeli, Ehsan, Altman, Russ, Arora, Simran, von Arx, Sydney, Bernstein, Michael S., Bohg, Jeannette, Bosselut, Antoine, Brunskill, Emma et al. · 2021 · arXiv
Related (10)
- Forgetting curves: implications for connectionist modelsSverker Sikström · 2002 · Cognitive Psychology
- Using Pseudo-Recurrent Connectionist Networks to Solve the Problem of Sequential LearningRobert M. French · 1997
- A model of memory, learning and recognitionB. Hoeneisen · 2002 · arXiv (Cornell University)
- Are multi‐layer backpropagation networks catastrophically amnesic?Makoto Yamaguchi · 2004 · Scandinavian Journal of Psychology
- Models of learning and memoryDavid M. Eagleman, P. Read Montague · 2002
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Connectionist models of recognition memory: Constraints imposed by learning and forgetting functions. https://app.cochat.ai/papers/10.1037//0033-295x.97.2.285
- The paper
- Ratcliff, R. (1990). Connectionist models of recognition memory: Constraints imposed by learning and forgetting functions. Psychological Review. https://doi.org/10.1037//0033-295x.97.2.285
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.