2026-09-21T17:41:07Z https://www.ideals.illinois.edu/oai-pmh

oai:www.ideals.illinois.edu:2142/81622 2023-07-11 col_2142_5131 col_2142_10761 com_2142_5130 com_2142_10755 com_2142_234

Gary Dell Roth, Dan Harris, Harlan D. 2015-09-25T20:19:33Z 2015-09-25T20:19:33Z 10000-01-01 2003 2003 Another significant goal of this work was to identify the inductive biases of each algorithm, so that they can be fairlycompared with each other. By examining their biases and properties using the results presented here, it is possible to view 2Pes as a particular generalization of the Winnow algorithm, and IDBD as a further generalization of 2Pes. Understanding these relationships furthers the potential of attribute-efficient algorithms for real-world applications. Made available in DSpace on 2015-09-25T20:19:33Z (GMT). No. of bitstreams: 2 license.txt: 4848 bytes, checksum: 96035ab3f5e1c23cc7138a224ce498bd (MD5) 3101855.pdf: 4540067 bytes, checksum: 5d78ca920fc1799b4531410f6021c53f (MD5) Previous issue date: 2003 Embargo set by: Seth Robbins for item 82903 Lift date: Forever Reason: Restricted to the U of I community idenfinitely during batch ingest of legacy ETDs Restricted to the U of I community idenfinitely during batch ingest of legacy ETDs U of I Only 90 p. Thesis (Ph.D.)--University of Illinois at Urbana-Champaign, 2003. http://hdl.handle.net/2142/81622 (MiAaPQ)AAI3101855 eng Artificial Intelligence New Algorithms for Attribute-Efficient on -Line Linear Learning text Computer Science Computer Science University of Illinois at Urbana-Champaign Dissertation Ph.D.