STDP-Compatible Approximation of Backpropagation in an Energy-Based Model
The DOI matches its Crossref record; 12 of the 12 references it cites were found in a registry or an index.
Abstract
We show that Langevin Markov chain Monte Carlo inference in an energy-based model with latent variables has the property that the early steps of inference, starting from a stationary point, correspond to propagating error gradients into internal layers, similar to backpropagation. The backpropagated error is with respect to output units that have received an outside driving force pushing them away from the stationary point. Backpropagated error gradients correspond to temporal derivatives with respect to the activation of hidden units. These lead to a weight update proportional to the product of the presynaptic firing rate and the temporal rate of change of the postsynaptic firing rate. Simulations and a theoretical argument suggest that this rate-based update rule is consistent with those associated with spike-timing-dependent plasticity. The ideas presented in this article could be an element of a theory for explaining how brains perform credit assignment in deep hierarchies as efficiently as backpropagation does, with neural computation corresponding to both approximate inference in continuous-valued latent variables and error backpropagation, at the same time.
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
Hopfield, J. J. (1984) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.81.10.3088 · Cited by 6,918
Bi, G.-Q., & Poo, M.-M. (1998) · The Journal of Neuroscience · doi:10.1523/jneurosci.18-24-10464.1998 · Cited by 4,744
(2010) · Journal of Machine Learning Research · doi:10.5555/1756006.1953039 · Cited by 4,051
Bienenstock, E., Cooper, L., & Munro, P. (1982) · The Journal of Neuroscience · doi:10.1523/jneurosci.02-01-00032.1982 · Cited by 2,896
An introduction to MCMC for machine learning.
Andrieu, C., de Freitas, N., Doucet, A., & Jordan, M. I. (2003) · Machine Learning · doi:10.1023/a:1020281327116 · Cited by 2,451
Hubara, I., Soudry, D., & Yaniv, R. E. (2016) · arXiv · doi:10.48550/arxiv.1602.02505 · Cited by 1,667
The Spike-Timing Dependence of Plasticity
Feldman, D. E. (2012) · Neuron · doi:10.1016/j.neuron.2012.08.001 · Cited by 1,071
Learning and relearning in Boltzmann machines
Hinton, G. E., & Sejnowski, T. J. (2001) · Graphical Models · doi:10.7551/mitpress/3349.003.0005 · Cited by 1,037
A Connection Between Score Matching and Denoising Autoencoders
Vincent, P. (2011) · Neural Computation · doi:10.1162/neco_a_00142 · Cited by 1,011 · cited 1×
“Note that the standard biological neuron models assume that R i ( s ) is a weighted sum of the input spikes (or of the input firing rates). error (Vincent, 2011; Alain & Bengio, 2013).”
BackgroundSpontaneous Cortical Activity Reveals Hallmarks of an Optimal Internal Model of the Environment
Berkes, P., Orbán, G., Lengyel, M., & Fiser, J. (2011) · Science · doi:10.1126/science.1195870 · Cited by 782
Friston, K. J., & Stephan, K. E. (2007) · Synthese · doi:10.1007/s11229-007-9237-y · Cited by 673
Phenomenological models of synaptic plasticity based on spike timing
Morrison, A., Diesmann, M., & Gerstner, W. (2008) · Biological Cybernetics · doi:10.1007/s00422-008-0233-1 · Cited by 593
Cited by
Deep Convolutional Neural Networks for Image Classification: A Comprehensive Review
Rawat, W., & Wang, Z. (2017) · Neural Computation · doi:10.1162/neco_a_00990 · Cited by 3,503
Deep learning in spiking neural networks
Tavanaei, A., Ghodrati, M., Kheradpisheh, S. R., Masquelier, T., & Maida, A. (2019) · Neural Networks · doi:10.1016/j.neunet.2018.12.002 · Cited by 1,386
Deep Learning With Spiking Neurons: Opportunities and Challenges
Pfeiffer, M., & Pfeil, T. (2018) · Frontiers in Neuroscience · doi:10.3389/fnins.2018.00774 · Cited by 766
Equilibrium Propagation: Bridging the Gap between Energy-Based Models and Backpropagation
Scellier, B., & Bengio, Y. (2017) · Frontiers in Computational Neuroscience · doi:10.3389/fncom.2017.00024 · Cited by 477
Self-citationTheories of Error Back-Propagation in the Brain
Whittington, J. C. R., & Bogacz, R. (2019) · Trends in Cognitive Sciences · doi:10.1016/j.tics.2018.12.005 · Cited by 420
“…is a diversity of ideas on how the back-propagation algorithm may be approximated in the brain [31 – 36]; however, we review the principles behind a set of related models [11,13,14,37] that have substantial connections with biological data while closely paralleling the back-propagation algorithm.”
BackgroundMethodInfluential
Metadata
- Authors
- Bengio, Y., Mesnard, T., Fischer, A., Zhang, S., & Wu, Y.
- Venue
- Neural Computation
- Publisher
- MIT Press - Journals
- Published
- 2017-03
- Volume
- 29
- Issue
- 3
- Pages
- 555-577
- ISSN
- 0899-7667 (ISSN-L)
- 1530-888X
- OpenAlex
- W2578935686
- Cited by
- 110
- References
- 12
- FWCI
- 7.22
- 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
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.