Article

Training a 3-node neural network is NP-complete

Authors:

Avrim Blum,

Ronald L. RivestAuthors Info & Claims

COLT '88: Proceedings of the first annual workshop on Computational learning theory

Pages 9 - 18

Published: 01 December 1988 Publication History

Abstract

No abstract available.

Cited By

View all

Lu TSchuurmans DBoutilier C(2018)Non-delusional Q-learning and value iterationProceedings of the 32nd International Conference on Neural Information Processing Systems10.5555/3327546.3327661(9971-9981)Online publication date: 3-Dec-2018
https://dl.acm.org/doi/10.5555/3327546.3327661
Li HXu ZTaylor GStuder CGoldstein T(2018)Visualizing the loss landscape of neural netsProceedings of the 32nd International Conference on Neural Information Processing Systems10.5555/3327345.3327535(6391-6401)Online publication date: 3-Dec-2018
https://dl.acm.org/doi/10.5555/3327345.3327535
Tsakonas AGabrys B(2013)A fuzzy evolutionary framework for combining ensemblesApplied Soft Computing10.1016/j.asoc.2012.12.02713:4(1800-1812)Online publication date: 1-Apr-2013
https://dl.acm.org/doi/10.1016/j.asoc.2012.12.027
Show More Cited By

Index Terms

Training a 3-node neural network is NP-complete
1. Computer systems organization
  1. Architectures
    1. Parallel architectures
      1. Multiple instruction, multiple data
2. Theory of computation

Recommendations

Training a 3-node neural network is NP-complete
NIPS'88: Proceedings of the 2nd International Conference on Neural Information Processing Systems

We consider a 2-layer, 3-node, n-input neural network whose nodes compute linear threshold functions of their inputs. We show that it is NP-complete to decide whether there exist weights and thresholds for the three nodes of this network so that it will ...
Complexity of training ReLU neural network
Abstract
In this paper, we explore some basic questions on the complexity of training neural networks with ReLU activation function. We show that it is NP-hard to train a two-hidden layer feedforward ReLU neural network. If dimension of the ...
Permanent oscillations in a 3-node recurrent neural network model

In this paper we discuss the existence of oscillations in a specific recurrent neural network: the 3-node network with two weight parameters and one time delay. Simple and practical criteria for fixing the range of the parameters in this network model ...

Comments

Information & Contributors

Information

Published In

COLT '88: Proceedings of the first annual workshop on Computational learning theory

December 1988

433 pages

Editors:
David Haussler
Univ. of California, Santa Cruz
,
Leonard Pitt
Univ. of Illinois, Urbana

Publisher

Morgan Kaufmann Publishers Inc.

San Francisco, CA, United States

Publication History

Published: 01 December 1988

Check for updates

Qualifiers

Article

Conference

COLT88

Sponsor:

SIGAI

COLT88: 1988 Working on Computational Learning Theory

August 3 - 5, 1988

Massachusetts, MIT, Cambridge, USA

Acceptance Rates

Overall Acceptance Rate 35 of 71 submissions, 49%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

13
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 17 Jan 2025

Other Metrics

View Author Metrics

Citations

Cited By

View all

Lu TSchuurmans DBoutilier C(2018)Non-delusional Q-learning and value iterationProceedings of the 32nd International Conference on Neural Information Processing Systems10.5555/3327546.3327661(9971-9981)Online publication date: 3-Dec-2018
https://dl.acm.org/doi/10.5555/3327546.3327661
Li HXu ZTaylor GStuder CGoldstein T(2018)Visualizing the loss landscape of neural netsProceedings of the 32nd International Conference on Neural Information Processing Systems10.5555/3327345.3327535(6391-6401)Online publication date: 3-Dec-2018
https://dl.acm.org/doi/10.5555/3327345.3327535
Tsakonas AGabrys B(2013)A fuzzy evolutionary framework for combining ensemblesApplied Soft Computing10.1016/j.asoc.2012.12.02713:4(1800-1812)Online publication date: 1-Apr-2013
https://dl.acm.org/doi/10.1016/j.asoc.2012.12.027
Lin TGiles C(2007)Group-Linking MethodIEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences10.1093/ietfec/e90-a.12.2916E90-A:12(2916-2929)Online publication date: 1-Dec-2007
https://dl.acm.org/doi/10.1093/ietfec/e90-a.12.2916
Bshouty NBurroughs L(2005)Maximizing Agreements with One-Sided Error with Applications to Heuristic LearningMachine Language10.1007/s10994-005-0464-559:1-2(99-123)Online publication date: 1-May-2005
https://dl.acm.org/doi/10.1007/s10994-005-0464-5
Riquelme JAguilar-Ruiz JValle C(2003)Supervised learning by means of accuracy-aware evolutionary algorithmsInformation Sciences: an International Journal10.1016/S0020-0255(03)00175-0156:3-4(173-188)Online publication date: 15-Nov-2003
https://dl.acm.org/doi/10.1016/S0020-0255%2803%2900175-0
Murthy S(1998)Automatic Construction of Decision Trees from DataData Mining and Knowledge Discovery10.1023/A:10097446302242:4(345-389)Online publication date: 1-Dec-1998
https://dl.acm.org/doi/10.1023/A%3A1009744630224
Brönnimann HGoodrich MMehlhorn K(1994)Almost optimal set covers in finite VC-dimensionProceedings of the tenth annual symposium on Computational geometry10.1145/177424.178029(293-302)Online publication date: 10-Jun-1994
https://dl.acm.org/doi/10.1145/177424.178029
Maass W(1993)Agnostic PAC-learning of functions on analog neural netsProceedings of the 7th International Conference on Neural Information Processing Systems10.5555/2987189.2987229(311-318)Online publication date: 29-Nov-1993
https://dl.acm.org/doi/10.5555/2987189.2987229
Maass WKosaraju RJohnson DAggarwal A(1993)Bounds for the computational power and learning complexity of analog neural netsProceedings of the twenty-fifth annual ACM symposium on Theory of Computing10.1145/167088.167193(335-344)Online publication date: 1-Jun-1993
https://dl.acm.org/doi/10.1145/167088.167193
Show More Cited By

Abstract

Cited By

Index Terms

Recommendations

Training a 3-node neural network is NP-complete

Complexity of training ReLU neural network

Permanent oscillations in a 3-node recurrent neural network model

Comments

Information

Published In

Sponsors

Publisher

Publication History

Check for updates

Qualifiers

Conference

Acceptance Rates

Contributors

Other Metrics

Bibliometrics

Article Metrics

Other Metrics

Citations

Cited By

View options

Figures

Other

Share

Share this Publication link

Share on social media

Affiliations