The DOI matches its Crossref record; 2 of the 2 references it cites were found in a registry or an index.
Markovian Architectural Bias of Recurrent Neural Networks
Abstract
In this paper, we elaborate upon the claim that clustering in the recurrent layer of recurrent neural networks (RNNs) reflects meaningful information processing states even prior to training [1], [2]. By concentrating on activation clusters in RNNs, while not throwing away the continuous state space network dynamics, we extract predictive models that we call neural prediction machines (NPMs). When RNNs with sigmoid activation functions are initialized with small weights (a common technique in the RNN community), the clusters of recurrent activations emerging prior to training are indeed meaningful and correspond to Markov prediction contexts. In this case, the extracted NPMs correspond to a class of Markov models, called variable memory length Markov models (VLMMs). In order to appreciate how much information has really been induced during the training, the RNN performance should always be compared with that of VLMMs and NPMs extracted before training as the "null" base models. Our arguments are supported by experiments on a chaotic symbolic sequence and a context-free language with a deep recursive structure. Index Terms-Complex symbolic sequences, information latching problem, iterative function systems, Markov models, recurrent neural networks (RNNs).
Overview
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.
Integrity signals
Registry
Cites
Statistics
Verification
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.
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
Cited by
Extended Dissipative State Estimation for Markov Jump Neural Networks With Unreliable Links
Shen, H., Zhu, Y., Zhang, L., & Park, J. H. (2017) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2015.2511196 · Cited by 489
Exponential stability of delayed recurrent neural networks with Markovian jumping parameters
Wang, Z., Liu, Y., Yu, L., & Liu, X. (2006) · Physics Letters A · doi:10.1016/j.physleta.2006.03.078 · Cited by 360
Gallicchio, C., & Micheli, A. (2010) · The 2010 International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2010.5596796 · Cited by 210
Metadata
- Authors
- Tino, P., Cernansky, M., & Benuskova, L.
- Venue
- IEEE Transactions on Neural Networks
- Published
- 2004-01
- Volume
- 15
- Issue
- 1
- Pages
- 6-15
- ISSN
- 1045-9227 (ISSN-L)
- OpenAlex
- W2070922095
- Cited by
- 172
- References
- 2
- FWCI
- 10.51
- 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: Markovian Architectural Bias of Recurrent Neural Networks. https://app.cochat.ai/papers/10.1109/tnn.2003.820839
- The paper
- Tino, P., Cernansky, M., & Benuskova, L. (2004). Markovian Architectural Bias of Recurrent Neural Networks. IEEE Transactions on Neural Networks. https://doi.org/10.1109/tnn.2003.820839
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.