Reducing the Ratio Between Learning Complexity and Number of Time Varying Variables in Fully Recurrent Nets
Open accessThe claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Learning to Control Fast-Weight Memories: An Alternative to Dynamic Recurrent Networks
Schmidhuber, J. (1992) · Neural Computation · doi:10.1162/neco.1992.4.1.131 · Cited by 357 · see citing works
Self-citation
Flagged first, then by citations
Cited by
Sorted by citations
Hutchins, D., Schlag, I., Wu, Y., Dyer, E., & Neyshabur, B. (2022) · arXiv · doi:10.48550/arxiv.2203.07852 · Cited by 43 · see citing works
Meta Learning Backpropagation And Improving It
Kirsch, L., & Schmidhuber, J. (2020) · arXiv · doi:10.48550/arxiv.2012.14905 · Cited by 19 · see citing works
Self-citationTitans: Learning to Memorize at Test Time
Behrouz, A., Zhong, P., & Mirrokni, V. (2025) · arXiv · doi:10.48550/arxiv.2501.00663 · Cited by 24 · see citing works
“The idea of seeing linear layers as the key-value (associative) memory system backs to fast weight programs, in which dynamic fast programs are incorporated into recurrent neural networks to serve as writable memory [71, 76, 114].”
Irie, K., Csordás, R., & Schmidhuber, J. (2022) · arXiv · doi:10.48550/arxiv.2202.05798 · Cited by 6 · see citing works
“We also note that Schmidhuber (1993) referred to the unnormalised attention used in the context of fast weight controllers as “internal spotlights of attention.””
BackgroundMethodSelf-citationNested Learning: The Illusion of Deep Learning Architectures
Behrouz, A., Razaviyayn, M., Zhong, P., & Mirrokni, V. (2025) · arXiv · doi:10.48550/arxiv.2512.24695 · Cited by 1 · see citing works
“The conceptualization of recurrence as key-value associative memory systems originates from Hopfield networks [86] and fast weight programmers, where dynamic fast programs function as writable memory within recurrent neural networks [62, 63, 87].”
Behrouz, A., Razaviyayn, M., Zhong, P., & Mirrokni, V. (2025) · arXiv · doi:10.48550/arxiv.2504.13173
ATLAS: Learning to Optimally Memorize the Context at Test Time
Behrouz, A., Li, Z., Kacham, P., Daliri, M., Deng, Y., Zhong, P., Razaviyayn, M., & Mirrokni, V. (2025) · arXiv · doi:10.48550/arxiv.2505.23735
- Authors
- Schmidhuber, J.
- Affiliations
- Technical University of Munich (DE)
- Corresponding author
- Schmidhuber, J.
- ORCID
- Schmidhuber, J.
- Venue
- ICANN ’93
- Publisher
- Springer London
- Published
- 1993
- Pages
- 460-463
- OpenAlex
- W185620388
- Cited by
- 34
- References
- 1
- Citations by year
- 2026: 2 · 2025: 1 · 2024: 4 · 2023: 3 · 2022: 5 · 2021: 4 · 2020: 5 · 2019: 5 · 2017: 2 · 2016: 1 · 2013: 1
- FWCI
- 0.00
- Type
- conference paper
- Language
- en
- Open access
- green
- mediatum.ub.tum.de
- Licence
- other-oa
- www.springer.com/tdm (tdm)
- Locations
- Springer eBooks (publishedVersion)
- mediaTUM – the media and publications repository of the Technical University Munich (Technical University Munich) (submittedVersion, other-oa)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Reservoir Computing
- Physical Sciences › Computer Science › Computational Theory and Mathematics › semigroups and automata theory
- Keywords
- sequence learning, real-time recurrent learning, backpropagation through time, computational complexity, space complexity
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
