Items where Author is "Ratsaby, Joel"

Article

Anthony, Martin ORCID: 0000-0002-7796-6044 and Ratsaby, Joel (2020) Large-width machine learning algorithm. Progress in Artificial Intelligence, 9 (3). 275 – 285. ISSN 2192-6360

Anthony, Martin ORCID: 0000-0002-7796-6044 and Ratsaby, Joel (2018) Large width nearest prototype classification on general distance spaces. Theoretical Computer Science, 738 (22). pp. 65-79. ISSN 0304-3975

Anthony, Martin ORCID: 0000-0002-7796-6044 and Ratsaby, Joel (2018) Large-width bounds for learning half-spaces on distance spaces. Discrete Applied Mathematics. ISSN 0166-218X

Anthony, Martin ORCID: 0000-0002-7796-6044 and Ratsaby, Joel (2017) Classification based on prototypes with spheres of influence. Information and Computation, 256. pp. 372-380. ISSN 0890-5401

Anthony, Martin ORCID: 0000-0002-7796-6044 and Ratsaby, Joel (2016) Multi-category classifiers and sample width. Journal of Computer and System Sciences, 82 (8). pp. 1223-1231. ISSN 0022-0000

Anthony, Martin ORCID: 0000-0002-7796-6044 and Ratsaby, Joel (2015) A probabilistic approach to case-based inference. Theoretical Computer Science, 589. pp. 61-75. ISSN 0304-3975

Anthony, Martin ORCID: 0000-0002-7796-6044 and Ratsaby, Joel (2014) A hybrid classifier based on boxes and nearest neighbors. Discrete Applied Mathematics, 172. pp. 1-11. ISSN 0166-218X

Anthony, Martin ORCID: 0000-0002-7796-6044 and Ratsaby, Joel (2014) Learning bounds via sample width for classifiers on finite metric spaces. Theoretical Computer Science, 529. pp. 2-10. ISSN 0304-3975

Anthony, Martin ORCID: 0000-0002-7796-6044 and Ratsaby, Joel (2012) Robust cutpoints in the logical analysis of numerical data. Discrete Applied Mathematics, 160 (4 - 5). pp. 355-364. ISSN 0166-218X

Anthony, Martin ORCID: 0000-0002-7796-6044 and Ratsaby, Joel (2010) Maximal width learning of binary functions. Theoretical Computer Science, 411 (1). pp. 138-147. ISSN 0304-3975

Book Section

Anthony, Martin and Ratsaby, Joel (2013) Maximal-margin case-based inference. In: Jin, Yaochu and Thomas, Spencer Angus, (eds.) 2013 13th Uk Workshop on Computational Intelligence (Ukci): Management School Foyer, University of Surrey, Guildford, Surrey, Uk. IEEE Conference Publications. IEEE, New York, USA, pp. 112-119. ISBN 9781479915682 (Submitted)

Anthony, Martin ORCID: 0000-0002-7796-6044 and Ratsaby, Joel (2013) Quantifying accuracy of learning via sample width. In: 2013 IEEE Symposium on Foundations of Computational Intelligence (FOCI). IEEE, Singapore, Singapore, pp. 84-90. ISBN 9781467359016

Monograph

Anthony, Martin ORCID: 0000-0002-7796-6044 and Ratsaby, Joel (2013) Large margin case-based reasoning. RUTCOR Research Reports (RRR 2-2013). Rutgers, The State University of New Jersey, Piscataway, New Jersey, USA.

Anthony, Martin ORCID: 0000-0002-7796-6044 and Ratsaby, Joel (2012) Sample width for multi-category classifiers. RUTCOR Research Reports (RRR 29-2012). RUTCOR, Rutgers University, Piscataway, New Jersey, USA.

Anthony, Martin ORCID: 0000-0002-7796-6044 and Ratsaby, Joel (2012) Learning on finite metric spaces. RUTCOR research reports (RRR 19-2012). Center for Operations Research, Rutgers University, Piscataway, New Jersey.

Anthony, Martin ORCID: 0000-0002-7796-6044 and Ratsaby, Joel (2012) Using boxes and proximity to classify data into several categories. RUTCOR research reports (RRR 7-2012). Center for Operations Research, Rutgers University, Piscataway, New Jersey.

Anthony, Martin ORCID: 0000-0002-7796-6044 and Ratsaby, Joel (2011) The performance of a new hybrid classifier based on boxes and nearest neighbors. RUTCOR research reports (RRR 17-2011). Center for Operations Research, Rutgers University, Piscataway, New Jersey.

Anthony, Martin ORCID: 0000-0002-7796-6044 and Ratsaby, Joel (2006) Maximal width learning of binary functions. CDAM research report series (CDAM-LSE-2006-11). Centre for Discrete and Applicable Mathematics, London School of Economics and Political Science, London, UK.

Conference or Workshop Item

Anthony, Martin and Ratsaby, Joel (2012) The performance of a new hybrid classifier based on boxes and nearest neighbors. In: International Symposium on Artificial Intelligence and Mathematics, 2012-01-09 - 2012-01-11, Fort Lauderdale FL, United States, USA. (Submitted)