Article

Free access

On learning Boolean functions

Author:

B. K. NatarajanAuthors Info & Claims

STOC '87: Proceedings of the nineteenth annual ACM symposium on Theory of computing

Pages 296 - 304

https://doi.org/10.1145/28395.28427

Published: 01 January 1987 Publication History

PDF eReader

Abstract

This paper deals with the learnability of Boolean functions. An intuitively appealing notion of dimensionality is developed and used to identify the most general class of Boolean function families that are learnable from polynomially many positive examples with one-sided error. It is then argued that although bounded DNF expressions lie outside this class, they must have efficient learning algorithms as they are well suited for expressing many human concepts. A framework that permits efficient learning of bounded DNF functions is identified.

References

[1]

Angluin, D., & Smith, C.H. (1983) Computing Surveys, Vol 16, No 3, Sept, pp237-269.

Digital Library

Google Scholar

[2]

Blumer, A., Ehrenfeucht, A., Haussler, D., & Warmuth, M. (1986). ACM Symposium on Theory of Computing, pp273-282.

Digital Library

Google Scholar

[3]

Feller, W. (1957). An introduction to Probability Theory and its Applications, John Wiley and Sons.

Google Scholar

[4]

Michalski, R.S., Carbonnell, J.G., & Mitchell, T.M. (1983). Machine Learning: An,Artificial Intelligence Approach, Tioga Publishing Co., Palo Alto, CA.

Digital Library

Google Scholar

[5]

Valiant, L.G. (1984). ACM Symposium on Theory of Computing, pp436-445.

Digital Library

Google Scholar

[6]

Vapnik, V.N. & Chervonenkis, A.Ya. (1971). Theory of Probability and its Applications, Vol 16, pp264-280.

Google Scholar

Cited By

View all

SASAO T(2024)On Easily Reconstructable Logic FunctionsIEICE Transactions on Information and Systems10.1587/transinf.2023LOP0001E107.D:8(913-921)Online publication date: 1-Aug-2024
https://doi.org/10.1587/transinf.2023LOP0001
Sasao T(2023)Easily Reconstructable Logic Functions2023 IEEE 53rd International Symposium on Multiple-Valued Logic (ISMVL)10.1109/ISMVL57333.2023.00014(12-17)Online publication date: May-2023
https://doi.org/10.1109/ISMVL57333.2023.00014
Seiffarth FHorváth TWrobel S(2023)Maximal Closed Set and Half-Space Separations in Finite Closure SystemsTheoretical Computer Science10.1016/j.tcs.2023.114105(114105)Online publication date: Jul-2023
https://doi.org/10.1016/j.tcs.2023.114105
Show More Cited By

Index Terms

On learning Boolean functions

Recommendations

Boolean functions with two distinct Walsh coefficients

Are there other Boolean functions having two distinct Walsh coefficients except affine Boolean functions and maximal nonlinear (i.e. bent) Boolean functions__ __ This paper proves that all Boolean functions with exactly two distinct Walsh coefficients ...
On the Symmetric Negabent Boolean Functions
INDOCRYPT '09: Proceedings of the 10th International Conference on Cryptology in India: Progress in Cryptology

We study the negabent Boolean functions which are symmetric. The Boolean function which has equal absolute spectral values under the nega-Hadamard transform is called a negabent function. For a bent function, the absolute spectral values are the same ...
A Note on Semi-bent and Hyper-bent Boolean Functions
Information Security and Cryptology
Abstract
Semi-bent and hyper-bent funcitons as two classes of Boolean functions with low Walsh transform, are applied in cryptography and commnunications. This paper considers a new class of semi-bent quadratic Boolean function and a generalization of a ...

Comments

Information & Contributors

Information

Published In

STOC '87: Proceedings of the nineteenth annual ACM symposium on Theory of computing

January 1987

471 pages

ISBN:0897912217

DOI:10.1145/28395

Editor:
Alfred V. Aho

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 01 January 1987

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Qualifiers

Article

Conference

STOC87

Sponsor:

SIGACT

STOC87: 19th Annual ACM Conference on Theory of Computing

New York, New York, USA

Acceptance Rates

STOC '87 Paper Acceptance Rate 50 of 165 submissions, 30%;

Overall Acceptance Rate 1,469 of 4,586 submissions, 32%

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

89
Total Citations
View Citations
755
Total Downloads

Downloads (Last 12 months)67
Downloads (Last 6 weeks)5

Reflects downloads up to 04 Oct 2024

Other Metrics

View Author Metrics

Citations

Cited By

View all

SASAO T(2024)On Easily Reconstructable Logic FunctionsIEICE Transactions on Information and Systems10.1587/transinf.2023LOP0001E107.D:8(913-921)Online publication date: 1-Aug-2024
https://doi.org/10.1587/transinf.2023LOP0001
Sasao T(2023)Easily Reconstructable Logic Functions2023 IEEE 53rd International Symposium on Multiple-Valued Logic (ISMVL)10.1109/ISMVL57333.2023.00014(12-17)Online publication date: May-2023
https://doi.org/10.1109/ISMVL57333.2023.00014
Seiffarth FHorváth TWrobel S(2023)Maximal Closed Set and Half-Space Separations in Finite Closure SystemsTheoretical Computer Science10.1016/j.tcs.2023.114105(114105)Online publication date: Jul-2023
https://doi.org/10.1016/j.tcs.2023.114105
Sasao TSasao T(2023)Easily Reconstructable FunctionsClassification Functions for Machine Learning and Data Mining10.1007/978-3-031-35347-5_9(91-105)Online publication date: 15-Jul-2023
https://doi.org/10.1007/978-3-031-35347-5_9
Liśkiewicz MLutter MReischuk R(2019)Proper learning of k-term DNF formulas from satisfying assignmentsJournal of Computer and System Sciences10.1016/j.jcss.2019.07.004Online publication date: Jul-2019
https://doi.org/10.1016/j.jcss.2019.07.004
Darnstädt MDoliwa TSimon HZilles S(2013)Order Compression SchemesAlgorithmic Learning Theory10.1007/978-3-642-40935-6_13(173-187)Online publication date: 2013
https://doi.org/10.1007/978-3-642-40935-6_13
Chhel FLardeux FGoëffon ASaubion FOssowski SLecca P(2012)Minimum multiple characterization of biological data using partially defined boolean formulasProceedings of the 27th Annual ACM Symposium on Applied Computing10.1145/2245276.2231998(1399-1405)Online publication date: 26-Mar-2012
https://dl.acm.org/doi/10.1145/2245276.2231998
Chhel FGoëffon ALafosse ALardeux FSaubion FHunault GBoureau TChu WWong WPalakal MHung C(2011)The bacterial strains characterization problemProceedings of the 2011 ACM Symposium on Applied Computing10.1145/1982185.1982213(108-109)Online publication date: 21-Mar-2011
https://dl.acm.org/doi/10.1145/1982185.1982213
Hanson S(2011)Learning and representation: Tensions at the interfaceBehavioral and Brain Sciences10.1017/S0140525X0008000613:03(511-518)Online publication date: 19-May-2011
https://doi.org/10.1017/S0140525X00080006
Weaver MKaplan S(2011)Connectionist learning and the challenge of real environmentsBehavioral and Brain Sciences10.1017/S0140525X0007999113:03(510-511)Online publication date: 19-May-2011
https://doi.org/10.1017/S0140525X00079991
Show More Cited By

View Options

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Cited By

Index Terms

Recommendations

Boolean functions with two distinct Walsh coefficients

On the Symmetric Negabent Boolean Functions

A Note on Semi-bent and Hyper-bent Boolean Functions

Comments

Published In

Sponsors

Publisher

Publication History

Permissions

Check for updates

Qualifiers

Conference

Acceptance Rates

Other Metrics

Article Metrics

Other Metrics

Cited By

PDF

eReader

Login options

Full Access

Abstract

References

Cited By

Index Terms

Recommendations

Boolean functions with two distinct Walsh coefficients

On the Symmetric Negabent Boolean Functions

A Note on Semi-bent and Hyper-bent Boolean Functions

Comments

Information

Published In

Sponsors

Publisher

Publication History

Permissions

Check for updates

Qualifiers

Conference

Acceptance Rates

Contributors

Other Metrics

Bibliometrics

Article Metrics

Other Metrics

Citations

Cited By

View options

PDF

eReader

Get Access

Login options

Full Access

Figures

Other

Share

Share this Publication link

Share on social media

Affiliations