How Inhibitory Oscillations Can Train Neural Networks and Punish Competitors
The DOI matches its Crossref record; 18 of the 18 references it cites were found in a registry or an index.
Abstract
We present a new learning algorithm that leverages oscillations in the strength of neural inhibition to train neural networks. Raising inhibition can be used to identify weak parts of target memories, which are then strengthened. Conversely, lowering inhibition can be used to identify competitors, which are then weakened. To update weights, we apply the Contrastive Hebbian Learning equation to successive time steps of the network. The sign of the weight change equation varies as a function of the phase of the inhibitory oscillation. We show that the learning algorithm can memorize large numbers of correlated input patterns without collapsing and that it shows good generalization to test patterns that do not exactly match studied patterns.
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
McClelland, J. L., McNaughton, B. L., & O'Reilly, R. C. (1995) · Psychological Review · doi:10.1037/0033-295x.102.3.419 · Cited by 5,256 · cited 1×
“Our model, like the backpropagation networks discussed by McClelland et al. (1995) and McCloskey and Cohen (1989), shows catastrophic interference when it is trained on one set of patterns and then trained on a different, similar set of patterns (i.”
MethodA learning algorithm for Boltzmann machines
Ackley, D. H., Hinton, G. E., & Sejnowski, T. J. (1985) · Cognitive Science · doi:10.1207/s15516709cog0901_7 · Cited by 3,402
Theta oscillations in the hippocampus
Buzsáki, G. (2002) · Neuron · doi:10.1016/s0896-6273(02)00586-x · Cited by 3,332
Bienenstock, E., Cooper, L., & Munro, P. (1982) · The Journal of Neuroscience · doi:10.1523/jneurosci.02-01-00032.1982 · Cited by 2,896
Simple memory: a theory for archicortex
Marr, D. (1971) · Philosophical Transactions of the Royal Society of London. B, Biological Sciences · doi:10.1098/rstb.1971.0078 · Cited by 2,771
Natural Image Statistics and Neural Representation
Simoncelli, E. P., & Olshausen, B. A. (2001) · Annual Review of Neuroscience · doi:10.1146/annurev.neuro.24.1.1193 · Cited by 2,460 · cited 1×
“ After repeated exposure to a set of patterns, the network shouldbe able tofill in missing pieces of those patterns, even if the patterns are highly correlated (insofar as real-worldinput patterns show a high degree of correlation; Simoncelli & Olshausen, 2001 ).”
BackgroundRemembering can cause forgetting: Retrieval dynamics in long-term memory.
Anderson, M. C., Bjork, R. A., & Bjork, E. L. (1994) · Journal of Experimental Psychology: Learning, Memory, and Cognition · doi:10.1037/0278-7393.20.5.1063 · Cited by 1,482
Norman, K. A., & O'Reilly, R. C. (2003) · Psychological Review · doi:10.1037/0033-295x.110.4.611 · Cited by 1,312
Self-citationHippocampal synaptic enhancement and information storage within a distributed memory system
McNaughton, B. L., & Morris, R. G. M. (1987) · Trends in Neurosciences · doi:10.1016/0166-2236(87)90011-7 · Cited by 1,304 · cited 1×
“McClelland et al. contrast this with hippocampal learning, which (according to their model) involves assigning distinct representations to input patterns regardless of their similarity; this property allows the hippocampus to do one-trial memorization but hurts its ability to generalize to new patterns based on simila…”
BackgroundGeneralization of back-propagation to recurrent neural networks
Pineda, F. J. (1987) · Physical Review Letters · doi:10.1103/physrevlett.59.2229 · Cited by 931 · cited 1×
“Methods for Recurrent and Non-Recurrent Backpropagation Simulations For our simulations using the Almeida-Pineda (A-P) recurrent backpropagation algorithm (Almeida, 1989; Pineda, 1987 ), we used the rbp++ program contained in the PDP++ neural network software package.8 For our simulations using the (nonrecurrent) back…”
Method
Cited by
A unified framework for inhibitory control
Munakata, Y., Herd, S. A., Chatham, C. H., Depue, B. E., Banich, M. T., & O’Reilly, R. C. (2011) · Trends in Cognitive Sciences · doi:10.1016/j.tics.2011.07.011 · Cited by 699
A complementary systems account of word learning: neural and behavioural evidence
Davis, M. H., & Gaskell, M. G. (2009) · Philosophical Transactions of the Royal Society B: Biological Sciences · doi:10.1098/rstb.2009.0111 · Cited by 572
Hsieh, L.-T., & Ranganath, C. (2014) · NeuroImage · doi:10.1016/j.neuroimage.2013.08.003 · Cited by 525
“Another account of FMT is that theta oscillations might have systematic effects on strong and weak representations in a neural network (Norman et al., 2005, 2006a, 2007).”
BackgroundMethodResultInfluentialSchapiro, A. C., Turk-Browne, N. B., Botvinick, M. M., & Norman, K. A. (2017) · Philosophical Transactions of the Royal Society B: Biological Sciences · doi:10.1098/rstb.2016.0049 · Cited by 487
Self-citationBanich, M. T., Mackiewicz, K. L., Depue, B. E., Whitmer, A. J., Miller, G. A., & Heller, W. (2009) · Neuroscience & Biobehavioral Reviews · doi:10.1016/j.neubiorev.2008.09.010 · Cited by 343
Metadata
- Authors
- Norman, K. A., Newman, E., Detre, G., & Polyn, S.
- Venue
- Neural Computation
- Publisher
- MIT Press - Journals
- Published
- 2006-07
- Volume
- 18
- Issue
- 7
- Pages
- 1577-1610
- ISSN
- 0899-7667 (ISSN-L)
- 1530-888X
- OpenAlex
- W2127317012
- Cited by
- 117
- References
- 18
- FWCI
- 3.83
- Type
- journal article
- Language
- en
- Open access
- closed
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: How Inhibitory Oscillations Can Train Neural Networks and Punish Competitors. https://app.cochat.ai/papers/10.1162/neco.2006.18.7.1577
- The paper
- Norman, K. A., Newman, E., Detre, G., & Polyn, S. (2006). How Inhibitory Oscillations Can Train Neural Networks and Punish Competitors. Neural Computation. https://doi.org/10.1162/neco.2006.18.7.1577
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.