Meta-learning synaptic plasticity and memory addressing for continual familiarity detection
Open accessThe DOI matches its Crossref record; 23 of the 23 references it cites were found in a registry or an index.
Abstract
Summary Over the course of a lifetime, we process a continual stream of information. Extracted from this stream, memories must be efficiently encoded and stored in an addressable manner for retrieval. To explore potential mechanisms, we consider a familiarity detection task where a subject reports whether an image has been previously encountered. We design a feedforward network endowed with synaptic plasticity and an addressing matrix, meta-learned to optimize familiarity detection over long intervals. We find that anti-Hebbian plasticity leads to better performance than Hebbian and replicates experimental results such as repetition suppression. A combinatorial addressing function emerges, selecting a unique neuron as an index into the synaptic memory matrix for storage or retrieval. Unlike previous models, this network operates continuously, and generalizes to intervals it has not been trained on. Our work suggests a biologically plausible mechanism for continual learning, and demonstrates an effective application of machine learning for neuroscience discovery.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
Learning representations by back-propagating errors
Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986) · Nature · doi:10.1038/323533a0 · Cited by 31,892
Neural networks and physical systems with emergent collective computational abilities.
Hopfield, J. J. (1982) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.79.8.2554 · Cited by 19,270 · cited 1×
“Classical models of memory rely on ‘‘content-based addressing’’ (Hopfield, 1982), whereby a partial cue elicits recall of the full memory through recurrent dynamics, but do not explicitly select which synapses store the memory.”
BackgroundOvercoming catastrophic forgetting in neural networks
Kirkpatrick, J., Pascanu, R., Rabinowitz, N., Veness, J., Desjardins, G., Rusu, A. A., Milan, K., Quan, J., Ramalho, T., Grabska-Barwinska, A., et al. (2017) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1611835114 · Cited by 7,899
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1512.03385 · Cited by 4,196
Synaptic plasticity: taming the beast
Abbott, L. F., & Nelson, S. B. (2000) · Nature Neuroscience · doi:10.1038/81453 · Cited by 2,263
Self-citationRepetition and the brain: neural models of stimulus-specific effects
Grill-Spector, K., Henson, R., & Martin, A. (2006) · Trends in Cognitive Sciences · doi:10.1016/j.tics.2005.11.006 · Cited by 2,256 · cited 2×
“In this case, the hidden-layer activity is lower for a familiar stimulus, consistent with experimental results of repetition suppression (Grill-Spector et al., 2006; Meyer and Rust, 2018; Xiang and Brown, 1998).”
BackgroundResultContinual Learning Through Synaptic Intelligence
Zenke, F., Poole, B., & Ganguli, S. (2017) · arXiv · doi:10.48550/arxiv.1703.04200 · Cited by 1,784
Hybrid computing using a neural network with dynamic external memory
Graves, A., Wayne, G., Reynolds, M., Harley, T., Danihelka, I., Grabska-Barwińska, A., Colmenarejo, S. G., Grefenstette, E., Ramalho, T., Agapiou, J., et al. (2016) · Nature · doi:10.1038/nature20101 · Cited by 1,412
Distributed representations, simple recurrent networks, and grammatical structure
Elman, J. L. (1991) · Machine Learning · doi:10.1007/bf00114844 · Cited by 1,354
Norman, K. A., & O'Reilly, R. C. (2003) · Psychological Review · doi:10.1037/0033-295x.110.4.611 · Cited by 1,312
Visual long-term memory has a massive storage capacity for object details
Brady, T. F., Konkle, T., Alvarez, G. A., & Oliva, A. (2008) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.0803390105 · Cited by 1,106 · cited 2×
“More recent behavioral work has further demonstrated an impressive capacity in a continual setting, the error rate as a function of the number of intervening items exhibiting a ‘‘power law of forgetting’’ (Brady et al., 2008) and theoretical studies showing that this is achievable by synapses with metaplasticity (Fusi…”
BackgroundMethodGraves, A., Wayne, G., & Danihelka, I. (2014) · arXiv · doi:10.48550/arxiv.1410.5401 · Cited by 1,058
Standing, L. (1973) · Quarterly Journal of Experimental Psychology · doi:10.1080/14640747308400340 · Cited by 968 · cited 2×
“…plasticity mechanisms for familiarity detection (Bogacz and Brown, 2003) focused on a paradigm used in classic studies of recognition memory (Standing, 1973) in which subjects are serially presented an entire dataset and later asked to identify which stimulus is familiar in a…”
BackgroundInfluentialHierarchical process memory: memory as an integral component of information processing
Hasson, U., Chen, J., & Honey, C. J. (2015) · Trends in Cognitive Sciences · doi:10.1016/j.tics.2015.04.006 · Cited by 749
A Neural Mechanism for Working and Recognition Memory in Inferior Temporal Cortex
Miller, E. K., Li, L., & Desimone, R. (1991) · Science · doi:10.1126/science.1962197 · Cited by 706 · cited 1×
“have been observed as reductions in responses to repeated presentations of a stimulus, a phenomenon known as repetition suppression (Grill-Spector et al., 2006; Meyer and Rust, 2018; Miller et al., 1991; Xiang and Brown, 1998).”
BackgroundCascade Models of Synaptically Stored Memories
Fusi, S., Drew, P. J., & Abbott, L. F. (2005) · Neuron · doi:10.1016/j.neuron.2005.02.001 · Cited by 569 · cited 1×
“…impressive capacity in a continual setting, the error rate as a function of the number of intervening items exhibiting a ‘‘power law of forget-ting’’ (Brady et al., 2008) and theoretical studies showing that this is achievable by synapses with metaplasticity (Fusi et al., 2005; Ji-An et al., 2019).”
BackgroundSelf-citationRepresentation of retrieval confidence by single neurons in the human medial temporal lobe
Rutishauser, U., Ye, S., Koroma, M., Tudusciuc, O., Ross, I. B., Chung, J. M., & Mamelak, A. N. (2015) · Nature Neuroscience · doi:10.1038/nn.4041 · Cited by 147
Comparison of computational models of familiarity discrimination in the perirhinal cortex
Bogacz, R., & Brown, M. W. (2003) · Hippocampus · doi:10.1002/hipo.10093 · Cited by 134 · cited 15×
“556 B Lead contact B Materials availability B Data and code availability d METHOD DETAILS B Continual familiarity detection task B HebbFF and RNN training B Bogacz-Brown (Bogacz and Brown, 2003) model implementation B Training FLD and SCC decoders B Simultaneous classification and familiarity detection B Idealized mod…”
BackgroundMethodResultInfluential
Cited by
Curiosity: primate neural circuits for novelty and information seeking
Monosov, I. E. (2024) · Nature Reviews Neuroscience · doi:10.1038/s41583-023-00784-9 · Cited by 44
Visual information processing through the interplay between fine and coarse signal pathways
Zou, X., Ji, Z., Zhang, T., Huang, T., & Wu, S. (2023) · Neural Networks · doi:10.1016/j.neunet.2023.07.048 · Cited by 9
Metadata
- Authors
- Tyulmankov, D., Yang, G. R., & Abbott, L. F.
- Venue
- Neuron
- Publisher
- Elsevier BV
- Published
- 2022-02
- Volume
- 110
- Issue
- 3
- Pages
- 544-557.e8
- ISSN
- 0896-6273 (ISSN-L)
- OpenAlex
- W3215137167
- Cited by
- 51
- References
- 23
- FWCI
- 3.78
- Type
- journal article
- Language
- en
- Open access
- bronze
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
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.