Backpropagation through time and the brain
Open accessThe DOI matches its Crossref record; 25 of the 25 references it cites were found in a registry or an index.
Abstract
It has long been speculated that the backpropagation-of-error algorithm (backprop) may be a model of how the brain learns. Backpropagation-through-time (BPTT) is the canonical temporal-analogue to backprop used to assign credit in recurrent neural networks in machine learning, but there's even less conviction about whether BPTT has anything to do with the brain. Even in machine learning the use of BPTT in classic neural network architectures has proven insufficient for some challenging temporal credit assignment (TCA) problems that we know the brain is capable of solving. Nonetheless, recent work in machine learning has made progress in solving difficult TCA problems by employing novel memory-based and attention-based architectures and algorithms, some of which are brain inspired. Importantly, these recent machine learning methods have been developed in the context of, and with reference to BPTT, and thus serve to strengthen BPTT's position as a useful normative guide for thinking about temporal credit assignment in artificial and biological systems alike.
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
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
Learning long-term dependencies with gradient descent is difficult
Bengio, Y., Simard, P., & Frasconi, P. (1994) · IEEE Transactions on Neural Networks · doi:10.1109/72.279181 · Cited by 8,542
Memory and the hippocampus: A synthesis from findings with rats, monkeys, and humans.
Squire, L. R. (1992) · Psychological Review · doi:10.1037/0033-295x.99.2.195 · Cited by 5,376
WaveNet: a generative model for raw audio
Oord, A. V. D., Dieleman, S., Zen, H., Simonyan, K., Vinyals, O., Graves, A., Kalchbrenner, N., Senior, A., & Kavukcuoglu, K. (2016) · arXiv · doi:10.48550/arxiv.1609.03499 · Cited by 4,911
Backpropagation through time: what it does and how to do it
Werbos, P. J. (1990) · Proceedings of the IEEE · doi:10.1109/5.58337 · Cited by 4,879
A Learning Algorithm for Continually Running Fully Recurrent Neural Networks
Williams, R. J., & Zipser, D. (1989) · Neural Computation · doi:10.1162/neco.1989.1.2.270 · Cited by 4,369
Maass, W., Natschläger, T., & Markram, H. (2002) · Neural Computation · doi:10.1162/089976602760407955 · Cited by 4,025
Categorical Reparameterization with Gumbel-Softmax
Jang, E., Gu, S., & Poole, B. (2016) · arXiv · doi:10.48550/arxiv.1611.01144 · Cited by 3,616
Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
Cho, K., van Merrienboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. (2014) · arXiv · doi:10.48550/arxiv.1406.1078 · Cited by 3,317
The organization of recent and remote memories
Frankland, P. W., & Bontempi, B. (2005) · Nature Reviews Neuroscience · doi:10.1038/nrn1607 · Cited by 2,138
Performance-optimized hierarchical models predict neural responses in higher visual cortex
Yamins, D. L. K., Hong, H., Cadieu, C. F., Solomon, E. A., Seibert, D., & DiCarlo, J. J. (2014) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1403112111 · Cited by 1,924
Reverse replay of behavioural sequences in hippocampal place cells during the awake state
Foster, D. J., & Wilson, M. A. (2006) · Nature · doi:10.1038/nature04587 · Cited by 1,727
Coordinated memory replay in the visual cortex and hippocampus during sleep
Ji, D., & Wilson, M. A. (2007) · Nature Neuroscience · doi:10.1038/nn1825 · Cited by 1,669
Competitive learning: From interactive activation to adaptive resonance
Grossberg, S. (1987) · Cognitive Science · doi:10.1111/j.1551-6708.1987.tb00862.x · Cited by 1,471
Forward models: supervised learning with a distal teacher
Jordan, M. I., & Rumelhart, D. E. (1992) · Cognitive Science · doi:10.1207/s15516709cog1603_1 · Cited by 1,451
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
Sukhbaatar, S., Szlam, A., Weston, J., & Fergus, R. (2015) · arXiv · doi:10.48550/arxiv.1503.08895 · Cited by 1,345
Graves, A., Wayne, G., & Danihelka, I. (2014) · arXiv · doi:10.48550/arxiv.1410.5401 · Cited by 1,058
Cadieu, C. F., Hong, H., Yamins, D. L. K., Pinto, N., Ardila, D., Solomon, E. A., Majaj, N. J., & DiCarlo, J. J. (2014) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1003963 · Cited by 824
Memory Transformation and Systems Consolidation
Winocur, G., & Moscovitch, M. (2011) · Journal of the International Neuropsychological Society · doi:10.1017/s1355617711000683 · Cited by 557
Learning in spiking neural networks by reinforcement of stochastic synaptic transmission
Seung, H. S. (2003) · Neuron · doi:10.1016/s0896-6273(03)00761-x · Cited by 340
Reverse replay of hippocampal place cells is uniquely modulated by changing reward
Ambrose, R. E., Pfeiffer, B. E., & Foster, D. J. (2016) · Neuron · doi:10.1016/j.neuron.2016.07.047 · Cited by 292
Bliss, T. V. P., & Lømo, T. (1973) · The Journal of Physiology · doi:10.1113/jphysiol.1973.sp010273 · Cited by 135
Scaling Memory-Augmented Neural Networks with Sparse Reads and Writes
Rae, J. W., Hunt, J. J., Harley, T., Danihelka, I., Senior, A., Wayne, G., Graves, A., & Lillicrap, T. P. (2016) · arXiv · doi:10.48550/arxiv.1610.09027 · Cited by 89
Self-citationOptimizing Agent Behavior over Long Time Scales by Transporting Value
Hung, C.-C., Lillicrap, T., Abramson, J., Wu, Y., Mirza, M., Carnevale, F., Ahuja, A., & Wayne, G. (2018) · arXiv · doi:10.48550/arxiv.1810.06721 · Cited by 75
Self-citation
Cited by
Embedded Devices for Neuromorphic Time-Series Assessment
Mazumder, A. N., Hosseini, M., & Mohsenin, T. (2022) · Research Explorer (The University of Manchester) · doi:10.13016/m2ksy0-wxr3 · Cited by 652
A solution to the learning dilemma for recurrent networks of spiking neurons
Bellec, G., Scherr, F., Subramoney, A., Hajek, E., Salaj, D., Legenstein, R., & Maass, W. (2020) · Nature Communications · doi:10.1038/s41467-020-17236-y · Cited by 506
Enabling Spike-Based Backpropagation for Training Deep Neural Network Architectures
Lee, C., Sarwar, S. S., Panda, P., Srinivasan, G., & Roy, K. (2020) · Frontiers in Neuroscience · doi:10.3389/fnins.2020.00119 · Cited by 434
Supervised learning in spiking neural networks: A review of algorithms and evaluations
Wang, X., Lin, X., & Dang, X. (2020) · Neural Networks · doi:10.1016/j.neunet.2020.02.011 · Cited by 277
Hooker, S. (2021) · Communications of the ACM · doi:10.1145/3467017 · Cited by 211
“Our own intelligence relies on decentralized local updates which surface a global signal in ways that are still not well understood (Lillicrap & Santoro, 2019; Marblestone et al., 2016; Bi & Poo, 1998).”
Background
Metadata
- Authors
- Lillicrap, T. P., & Santoro, A.
- Venue
- Current Opinion in Neurobiology
- Publisher
- Elsevier BV
- Published
- 2019-04
- Volume
- 55
- Pages
- 82-89
- ISSN
- 0959-4388 (ISSN-L)
- OpenAlex
- W2922004937
- Cited by
- 142
- References
- 25
- FWCI
- 1.65
- Type
- journal article
- Language
- en
- Open access
- hybrid
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.