An introduction to computational learning theory /

Saved in:
書目詳細資料
主要作者: Kearns, Michael J.
其他作者: Vazirani, Umesh Virkumar
格式: 圖書
語言:English
出版: Cambridge, Mass. : MIT Press, c1994.
主題:
LEADER 01526cam a2200325 a 4500
001 c000213272
003 CARM
005 20060207104750.0
008 940426s1994 maua b 001 0 eng
010 |a 94016588 
019 1 |a 10942506  |5 LACONCORD2021 
020 |a 0262111934 
035 |a (OCoLC)30476515  |5 LACONCORD2021 
040 |a TOC  |b eng  |c TOC  |d NU 
050 0 0 |a Q325.5  |b .K44 1994 
082 0 0 |a 006.3  |2 20 
100 1 |a Kearns, Michael J. 
245 1 3 |a An introduction to computational learning theory /  |c Michael J. Kearns, Umesh V. Vazirani. 
260 |a Cambridge, Mass. :  |b MIT Press,  |c c1994. 
300 |a xii, 207 p. :  |b ill. ;  |c 24 cm. 
504 |a Includes bibliographical references (p. [193]-203) and index. 
505 0 |a 1. The Probably Approximately Correct Learning Model -- 2. Occam's Razor -- 3. The Vapnik-Chervonenkis Dimension -- 4. Weak and Strong Learning -- 5. Learning in the Presence of Noise -- 6. Inherent Unpredictability -- 7. Reducibility in PAC Learning -- 8. Learning Finite Automata by Experimentation -- 9. Appendix: Some Tools for Probabilistic Analysis. 
650 0 |a Machine learning. 
650 0 |a Artificial intelligence. 
650 0 |a Algorithms. 
650 0 |a Neural networks (Computer science) 
700 1 |a Vazirani, Umesh Virkumar. 
852 8 |b CARM  |h A2:AM09G0  |i C07935  |p 0273411  |f BK 
999 f f |i 164540e3-11c9-578c-9316-3f2c4928c4fd  |s e0fc8dd4-0219-5774-8ab2-ace734025c13 
952 f f |p Can circulate  |a CAVAL  |b CAVAL  |c CAVAL  |d CARM 1 Store  |e C07935  |f A2:AM09G0  |h Other scheme  |i book  |m 0273411