The DOI matches its Crossref record; 27 of the 27 references it cites were found in a registry or an index.
Computational capabilities of recurrent NARX neural networks
Abstract
Recently, fully connected recurrent neural networks have been proven to be computationally rich-at least as powerful as Turing machines. This work focuses on another network which is popular in control applications and has been found to be very effective at learning a variety of problems. These networks are based upon Nonlinear AutoRegressive models with eXogenous Inputs (NARX models), and are therefore called NARX networks. As opposed to other recurrent networks, NARX networks have a limited feedback which comes only from the output neuron rather than from hidden states. They are formalized by y(t)=Psi(u(t-n(u)), ..., u(t-1), u(t), y(t-n(y)), ..., y(t-1)) where u(t) and y(t) represent input and output of the network at time t, n(u) and n(y) are the input and output order, and the function Psi is the mapping performed by a Multilayer Perceptron. We constructively prove that the NARX networks with a finite number of parameters are computationally as strong as fully connected recurrent networks and thus Turing machines. We conclude that in theory one can use the NARX models, rather than conventional recurrent networks without any computational loss even though their feedback is limited. Furthermore, these results raise the issue of what amount of feedback or recurrence is necessary for any network to be Turing equivalent and what restrictions on feedback limit computational power.
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
A logical calculus of the ideas immanent in nervous activity
McCulloch, W. S., & Pitts, W. (1943) · The Bulletin of Mathematical Biophysics · doi:10.1007/bf02478259 · Cited by 18,566
Approximation by superpositions of a sigmoidal function
Cybenko, G. (1989) · Mathematics of Control, Signals, and Systems · doi:10.1007/bf02551274 · Cited by 13,883
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
Identification and control of dynamical systems using neural networks
Narendra, K. S., & Parthasarathy, K. (1990) · IEEE Transactions on Neural Networks · doi:10.1109/72.80202 · Cited by 8,014
On the approximate realization of continuous mappings by neural networks
Funahashi, K.-I. (1989) · Neural Networks · doi:10.1016/0893-6080(89)90003-8 · Cited by 4,206
Computation: Finite and Infinite Machines.
Clarke, D. A., & Minsky, M. L. (1968) · The American Mathematical Monthly · doi:10.2307/2313471 · Cited by 2,583
Switching and Finite Automata Theory
Kohavi, Z., & Jha, N. K. (2009) · Cambridge University Press eBooks · doi:10.1017/cbo9780511816239 · Cited by 1,766
Input-output parametric models for non-linear systems Part I: deterministic non-linear systems
LEONTARITIS, I. J., & BILLINGS, S. A. (1985) · International Journal of Control · doi:10.1080/0020718508961129 · Cited by 1,147
Input-output parametric models for non-linear systems Part II: stochastic non-linear systems
LEONTARITIS, I. J., & BILLINGS, S. A. (1985) · International Journal of Control · doi:10.1080/0020718508961130 · Cited by 1,065
Non-linear system identification using neural networks
CHEN, S., BILLINGS, S. A., & GRANT, P. M. (1990) · International Journal of Control · doi:10.1080/00207179008934126 · Cited by 1,043
Learning long-term dependencies in NARX recurrent neural networks
Lin, T., Horne, B. G., Tino, P., & Giles, C. L. (1996) · IEEE Transactions on Neural Networks · doi:10.1109/72.548162 · Cited by 784
Self-citationOn the Computational Power of Neural Nets
Siegelmann, H. T., & Sontag, E. D. (1995) · Journal of Computer and System Sciences · doi:10.1006/jcss.1995.1013 · Cited by 692
Self-citationTuring computability with neural nets
Siegelmann, H. T., & Sontag, E. D. (1991) · Applied Mathematics Letters · doi:10.1016/0893-9659(91)90080-f · Cited by 377
Self-citationAnalog computation via neural networks
Siegelmann, H. T., & Sontag, E. D. (1994) · Theoretical Computer Science · doi:10.1016/0304-3975(94)90178-3 · Cited by 355
Self-citationThe induction of dynamical recognizers
Pollack, J. B. (1991) · Machine Learning · doi:10.1007/bf00114845 · Cited by 294
Sequential Machines and Automata Theory
Cooper, D. C. (1968) · The Computer Journal · doi:10.1093/comjnl/11.2.176 · Cited by 282
The gamma model—A new neural model for temporal processing
Vries, B. D., & Principe, J. C. (1992) · Neural Networks · doi:10.1016/s0893-6080(05)80035-8 · Cited by 254
FIR and IIR Synapses, a New Neural Network Architecture for Time Series Modeling
Back, A. D., & Tsoi, A. C. (1991) · Neural Computation · doi:10.1162/neco.1991.3.3.375 · Cited by 210
Local Feedback Multilayered Networks
Frasconi, P., Gori, M., & Soda, G. (1992) · Neural Computation · doi:10.1162/neco.1992.4.1.120 · Cited by 189
Comparison of four neural net learning methods for dynamic system identification
Qin, S.-Z., Su, H.-T., & McAvoy, T. J. (1992) · IEEE Transactions on Neural Networks · doi:10.1109/72.105425 · Cited by 184
Constructing deterministic finite-state automata in recurrent neural networks
Omlin, C. W., & Giles, C. L. (1996) · Journal of the ACM · doi:10.1145/235809.235811 · Cited by 178
Self-citationEfficient simulation of finite automata by neural nets
Alon, N., Dewdney, A. K., & Ott, T. J. (1991) · Journal of the ACM · doi:10.1145/103516.103523 · Cited by 93
Bounds on the complexity of recurrent neural network implementations of finite state machines
Horne, B. G., & Hush, D. R. (1996) · Neural Networks · doi:10.1016/0893-6080(95)00095-x · Cited by 85
Self-citationLearning a class of large finite state machines with a recurrent neural network
Giles, C. L., Horne, B. G., & Lin, T.-N. (1995) · Neural Networks · doi:10.1016/0893-6080(95)00041-0 · Cited by 63
Self-citationIdentification of Chemical Processes using Recurrent Networks
Su, H.-T., & McAvoy, T. J. (1991) · Proceedings of the ... American Control Conference/Proceedings of the American Control Conference · doi:10.23919/acc.1991.4791818 · Cited by 43
On the power of sigmoid neural networks
Kilian, J., & Siegelmann, H. T. (1993) · Conference on Learning Theory · doi:10.1145/168304.168321 · Cited by 32
Self-citationLearning long-term dependencies is not as difficult with NARX recurrent neural networks
Lin, T.-N., Horne, B. G., Peter Tiňo, B., & Giles, C. L. (1995) · University Libraries (University of Maryland) · Cited by 29
Self-citation
Cited by
Maier, H. R., & Dandy, G. C. (2000) · Environmental Modelling & Software · doi:10.1016/s1364-8152(99)00007-9 · Cited by 2,377
Learning long-term dependencies in NARX recurrent neural networks
Lin, T., Horne, B. G., Tino, P., & Giles, C. L. (1996) · IEEE Transactions on Neural Networks · doi:10.1109/72.548162 · Cited by 784
Self-citationLong-term time series prediction with the NARX network: An empirical evaluation
Menezes, J. M. P., & Barreto, G. A. (2008) · Neurocomputing · doi:10.1016/j.neucom.2008.01.030 · Cited by 446
Sharifzadeh, M., Sikinioti-Lock, A., & Shah, N. (2019) · Renewable and Sustainable Energy Reviews · doi:10.1016/j.rser.2019.03.040 · Cited by 381
Parmezan, A. R. S., Souza, V. M. A., & Batista, G. E. A. P. A. (2019) · Information Sciences · doi:10.1016/j.ins.2019.01.076 · Cited by 337
Metadata
- Authors
- Siegelmann, H. T., Horne, B. G., & Giles, C. L.
- Venue
- IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics)
- Published
- 1997-04
- Volume
- 27
- Issue
- 2
- Pages
- 208-215
- ISSN
- 1083-4419 (ISSN-L)
- 1941-0492
- OpenAlex
- W2171800554
- Cited by
- 455
- References
- 27
- FWCI
- 12.36
- 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.