Sequential Neural Networks as Automata
Open accessThe DOI matches its Crossref record; 7 of the 7 references it cites were found in a registry or an index.
Abstract
This work attempts to explain the types of computation that neural networks can perform by relating them to automata.We first define what it means for a real-time network with bounded precision to accept a language.A measure of network memory follows from this definition.We then characterize the classes of languages acceptable by various recurrent networks, attention, and convolutional networks.We find that LSTMs function like counter machines and relate convolutional networks to the subregular hierarchy.Overall, this work attempts to increase our understanding and ability to interpret neural networks through the lens of theory.These theoretical insights help explain neural computation, as well as the relationship between neural networks and natural language grammar.
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
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
Character-Aware Neural Language Models
Kim, Y., Jernite, Y., Sontag, D., & Rush, A. M. (2015) · arXiv · doi:10.48550/arxiv.1508.06615 · Cited by 1,530
Training with Noise is Equivalent to Tikhonov Regularization
Bishop, C. M. (1995) · Neural Computation · doi:10.1162/neco.1995.7.1.108 · Cited by 1,325
On the computational power of neural nets
Siegelmann, H. T., & Sontag, E. D. (1992) · Proceedings of the fifth annual workshop on Computational learning theory · doi:10.1145/130385.130432 · Cited by 238
On the Practical Computational Power of Finite Precision RNNs for Language Recognition
Weiss, G., Goldberg, Y., & Yahav, E. (2018) · Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) · doi:10.18653/v1/p18-2117 · Cited by 226 · cited 14×
“Definition 3.3 (GRU layer). zt = σ(W zxt + U zht−1 + b z) (18) rt = σ(W rxt + U rht−1 + b r) (19) ut = tanh ( Wuxt + U u(rt ht−1) + bu ) (20) ht = zt ht−1 + (1− zt) ut. (21) Weiss et al. (2018) observe that GRUs do not exhibit the same counter behavior as LSTMs on languages like anbn.”
BackgroundMethodInfluentialOn the Linguistic Capacity of Real-Time Counter Automata
Merrill, W. (2020) · arXiv · doi:10.48550/arxiv.2004.06866 · Cited by 12
Self-citation
Cited by
Theoretical Limitations of Self-Attention in Neural Sequence Models
Hahn, M. (2020) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00306 · Cited by 165
Generating meaning: active inference and the scope and limits of passive AI
Pezzulo, G., Parr, T., Cisek, P., Clark, A., & Friston, K. (2024) · Trends in Cognitive Sciences · doi:10.1016/j.tics.2023.10.002 · Cited by 80
“For example, it has been proven that learning a context-sensitive programming language is not possible using any fi nite set of exemplar code, and it is likely that the challenge is even greater for inferring meaning from natural languages [79].”
On the Ability and Limitations of Transformers to Recognize Formal Languages
Bhattamishra, S., Ahuja, K., & Goyal, N. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.576 · Cited by 48
“Theoretical connections of recurrent models have been established with counter languages (Merrill, 2019; Merrill et al., 2020; Mer-rill, 2020).”
BackgroundSaturated Transformers are Constant-Depth Threshold Circuits
Merrill, W., Sabharwal, A., & Smith, N. A. (2022) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00493 · Cited by 25
“Due to their autoregressive formulation, formal linguistic analysis of RNNs has often characterized their power by relating them to automata-theoretic classes of formal languages (Weiss et al., 2018; Peng et al., 2018; Merrill, 2019, inter alia ).”
BackgroundSelf-citationOn the Linguistic Capacity of Real-Time Counter Automata
Merrill, W. (2020) · arXiv · doi:10.48550/arxiv.2004.06866 · Cited by 12
Self-citation
Metadata
- Authors
- Merrill, W.
- Venue
- Proceedings of the Workshop on Deep Learning and Formal Languages: Building Bridges
- Published
- 2019
- Pages
- 1-13
- OpenAlex
- W2948981535
- Cited by
- 52
- References
- 7
- FWCI
- 9.46
- Type
- conference paper
- Language
- en
- Open access
- gold
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.