-
2
-
-
0002319152
-
The EM algorithm and information geometry in neural network learning
-
Amari, S. (1995), The EM algorithm and information geometry in neural network learning, Neural Comput. 7, 13-18.
-
(1995)
Neural Comput.
, vol.7
, pp. 13-18
-
-
Amari, S.1
-
3
-
-
0026966646
-
A training algorithm for optimal margin classifiers
-
ACM Press, New York
-
Boser, B. E., Guyon, I. M., and Vapnik, V. N. (1992), A training algorithm for optimal margin classifiers in "Proceedings, 5th Annual Workshop on Computational Learning Theory," pp. 144-152, ACM Press, New York.
-
(1992)
Proceedings, 5th Annual Workshop on Computational Learning Theory
, pp. 144-152
-
-
Boser, B.E.1
Guyon, I.M.2
Vapnik, V.N.3
-
4
-
-
0027274446
-
How to Use Expert Advice
-
Technical Report UCSC-CRL-94-33, Univ. of California, Santa Cruz, Computer Research Laboratory. An extended abstract appeared ACM Press, New York
-
Cesa-Bianchi, N., Freund, Y., Haussler, D., Helmbold, D. P., Schapire, R. E., and Warmuth, M. K. (1994), "How to Use Expert Advice," Technical Report UCSC-CRL-94-33, Univ. of California, Santa Cruz, Computer Research Laboratory. An extended abstract appeared in "Proceedings, 25th Annual ACM Symposium on the Theory of Computing," pp. 382-381, ACM Press, New York.
-
(1994)
Proceedings, 25th Annual ACM Symposium on the Theory of Computing
, pp. 382-1381
-
-
Cesa-Bianchi, N.1
Freund, Y.2
Haussler, D.3
Helmbold, D.P.4
Schapire, R.E.5
Warmuth, M.K.6
-
5
-
-
0030145382
-
Worst-case quadratic loss bounds for on-line prediction of linear functions by gradient descent
-
Cesa-Bianchi, N., Long, P., and Warmuth, M. K. (1996), Worst-case quadratic loss bounds for on-line prediction of linear functions by gradient descent, IEEE Trans. Neural Networks 7, 604-619.
-
(1996)
IEEE Trans. Neural Networks
, vol.7
, pp. 604-619
-
-
Cesa-Bianchi, N.1
Long, P.2
Warmuth, M.K.3
-
6
-
-
0004116989
-
-
MIT Press, Cambridge, MA
-
Cormen, T. H., Leiserson, C. E., and Rivest, R. L. (1990), "Introduction to Algorithms," MIT Press, Cambridge, MA.
-
(1990)
Introduction to Algorithms
-
-
Cormen, T.H.1
Leiserson, C.E.2
Rivest, R.L.3
-
7
-
-
0002629270
-
Maximum-likelihood from incomplete data via the EM algorithm
-
Dempster, A. P., Laird, N. M., and Rubin, D. B. (1977), Maximum-likelihood from incomplete data via the EM algorithm, J. Roy. Statist. Soc. Ser. B 39, 1-38.
-
(1977)
J. Roy. Statist. Soc. Ser. B
, vol.39
, pp. 1-38
-
-
Dempster, A.P.1
Laird, N.M.2
Rubin, D.B.3
-
8
-
-
0004164392
-
Tight Worst-Case loss bounds for Predicting with Expert Advice
-
Technical Report UCSC-CRL-94-36, Univ. California, Santa Cruz, Computer Research Laboratory. Partial results appeared Clarendon Press, Oxford
-
Haussler, D., Kivinen, J., and Warmuth, M. K. (1994), "Tight Worst-Case loss bounds for Predicting with Expert Advice," Technical Report UCSC-CRL-94-36, Univ. California, Santa Cruz, Computer Research Laboratory. Partial results appeared in "EuroCOLT '93," pp. 109-120, Clarendon Press, Oxford, and in "EuroCOLT '95," pp. 69-83, Springer, Berlin. To appear in IEEE Transactions on Information Theory.
-
(1994)
EuroCOLT '93
, pp. 109-120
-
-
Haussler, D.1
Kivinen, J.2
Warmuth, M.K.3
-
9
-
-
85030045874
-
EuroCOLT '95
-
Springer, Berlin. To appear
-
Haussler, D., Kivinen, J., and Warmuth, M. K. (1994), "Tight Worst-Case loss bounds for Predicting with Expert Advice," Technical Report UCSC-CRL-94-36, Univ. California, Santa Cruz, Computer Research Laboratory. Partial results appeared in "EuroCOLT '93," pp. 109-120, Clarendon Press, Oxford, and in "EuroCOLT '95," pp. 69-83, Springer, Berlin. To appear in IEEE Transactions on Information Theory.
-
IEEE Transactions on Information Theory
, pp. 69-83
-
-
-
10
-
-
0003807773
-
-
Prentice-Hall, Englewood Cliffs, NJ
-
Haykin, S. (1991), "Adaptive Filter Theory," 2nd ed., Prentice-Hall, Englewood Cliffs, NJ.
-
(1991)
"Adaptive Filter Theory," 2nd Ed.
-
-
Haykin, S.1
-
12
-
-
0346641007
-
Worst-case loss bounds for sigmoided linear neurons
-
MIT Press, Cambridge, MA
-
Helmbold, D. P., Kivinen, J., and Warmuth, M. K. (1996a), Worst-case loss bounds for sigmoided linear neurons, in "Advances in Neural Information Processing Systems 8," MIT Press, Cambridge, MA, pp. 309-315.
-
(1996)
Advances in Neural Information Processing Systems 8
, pp. 309-315
-
-
Helmbold, D.P.1
Kivinen, J.2
Warmuth, M.K.3
-
13
-
-
85030049790
-
A comparison of new and old algorithms for a mixture estimation problem
-
to appear
-
Helmbold, D. P., Schapire, R. E., Singer, Y., and Warmuth, M. K. (1996b), A comparison of new and old algorithms for a mixture estimation problem, Mach. Learning, to appear.
-
(1996)
Mach. Learning
-
-
Helmbold, D.P.1
Schapire, R.E.2
Singer, Y.3
Warmuth, M.K.4
-
14
-
-
0012802117
-
On-line portfolio selection using multiplicative updates
-
Morgan Kaufmann, San Francisco
-
Helmbold, D. P., Schapire, R. E., Singer, Y., and Warmuth, M. K. (1996c), On-line portfolio selection using multiplicative updates in "Proceedings, 13th International Conference on Machine Learning," Morgan Kaufmann, San Francisco, pp. 243-251.
-
(1996)
Proceedings, 13th International Conference on Machine Learning
, pp. 243-251
-
-
Helmbold, D.P.1
Schapire, R.E.2
Singer, Y.3
Warmuth, M.K.4
-
15
-
-
0029322423
-
On weak learning
-
Helmbold, D. P., and Warmuth, M. K. (1995), On weak learning, J. Comput. System Sci. 50, 551-573.
-
(1995)
J. Comput. System Sci.
, vol.50
, pp. 551-573
-
-
Helmbold, D.P.1
Warmuth, M.K.2
-
16
-
-
0002623785
-
Learning distributed representations of concepts
-
Erlbaum, Hillsdale, NJ
-
Hinton, G. E. (1986), Learning distributed representations of concepts, in "Proceedings, 8th Annual Conference of the Cognitive Science Society," pp. 1-12, Erlbaum, Hillsdale, NJ.
-
(1986)
Proceedings, 8th Annual Conference of the Cognitive Science Society
, pp. 1-12
-
-
Hinton, G.E.1
-
19
-
-
0001553979
-
Toward efficient agnostic learning
-
Kearns, M. J., Schapire, R. E., and Sellie, L. M. (1994), Toward efficient agnostic learning, Mach. Learning 17, 115-142.
-
(1994)
Mach. Learning
, vol.17
, pp. 115-142
-
-
Kearns, M.J.1
Schapire, R.E.2
Sellie, L.M.3
-
20
-
-
34250091945
-
Learning quickly when irrelevant attributes abound: A new linear-threshold algorithm
-
Littlestone, N. (1988), Learning quickly when irrelevant attributes abound: A new linear-threshold algorithm, Mach. Learning 2, 285-318.
-
(1988)
Mach. Learning
, vol.2
, pp. 285-318
-
-
Littlestone, N.1
-
21
-
-
85011913774
-
From on-line to batch learning
-
Morgan Kaufmann, San Mateo, CA
-
Littlestone, N. (1989), From on-line to batch learning in "Procedings, 2nd Annual Workshop on Computational Learning Theory," pp. 269-284, Morgan Kaufmann, San Mateo, CA.
-
(1989)
Procedings, 2nd Annual Workshop on Computational Learning Theory
, pp. 269-284
-
-
Littlestone, N.1
-
22
-
-
0003869088
-
-
Ph.D. thesis, Technical Report UCSC-CRL-89-11, Univ. of California, Santa Cruz, Computer Research Laboratory
-
Littlestone, N. (1989), "Mistake Bounds and Logarithmic Linear-threshold Learning Algorithms," Ph.D. thesis, Technical Report UCSC-CRL-89-11, Univ. of California, Santa Cruz, Computer Research Laboratory.
-
(1989)
Mistake Bounds and Logarithmic Linear-threshold Learning Algorithms
-
-
Littlestone, N.1
-
23
-
-
0000511449
-
Redundant noisy attributes, attribute errors, and linear threshold learning using Winnow
-
Morgan Kaufmann, San Mateo, CA
-
Littlestone, N. (1991), Redundant noisy attributes, attribute errors, and linear threshold learning using Winnow, in "Proceedings, 4th Annual Workshop on Computational Learning Theory," pp. 147-156, Morgan Kaufmann, San Mateo, CA.
-
(1991)
Proceedings, 4th Annual Workshop on Computational Learning Theory
, pp. 147-156
-
-
Littlestone, N.1
-
24
-
-
0001928981
-
On-line learning of linear functions
-
Littlestone, N., Long, P. M., and Warmuth, M. K. (1995), On-line learning of linear functions, J. Comput. Complexity 5, 1-23.
-
(1995)
J. Comput. Complexity
, vol.5
, pp. 1-23
-
-
Littlestone, N.1
Long, P.M.2
Warmuth, M.K.3
-
25
-
-
35148838877
-
The weighted majority algorithm
-
Littlestone, N., and Warmuth, M. K. (1994), The weighted majority algorithm, Inform, and Comput. 108, 212-261.
-
(1994)
Inform, and Comput.
, vol.108
, pp. 212-261
-
-
Littlestone, N.1
Warmuth, M.K.2
-
27
-
-
0003655416
-
-
Macmillan, New York
-
Royden, H. (1963), "Real Analysis," Macmillan, New York.
-
(1963)
Real Analysis
-
-
Royden, H.1
-
28
-
-
0008815095
-
On the worst-case analysis of temporal-difference learing algorithms
-
Morgan Kaufmann, San Francisco; Mach. Learning, to appear
-
Schapire, R. E., and Warmuth, M. K. (1994), On the worst-case analysis of temporal-difference learing algorithms, in "Proceedings, 11th International Conference on Machine Learning," pp. 266-274, Morgan Kaufmann, San Francisco; Mach. Learning, to appear.
-
(1994)
Proceedings, 11th International Conference on Machine Learning
, pp. 266-274
-
-
Schapire, R.E.1
Warmuth, M.K.2
-
29
-
-
85048665932
-
Aggregating strategies
-
Morgan Kaufmann, San Mateo, CA
-
Vovk, V. (1990), Aggregating strategies, in "Proceedings, 3rd Annual Workshop on Computational Learning Theory," pp. 371-383, Morgan Kaufmann, San Mateo, CA.
-
(1990)
Proceedings, 3rd Annual Workshop on Computational Learning Theory
, pp. 371-383
-
-
Vovk, V.1
-
30
-
-
0004113431
-
-
Prentice-Hall, Englewood Cliffs, NJ
-
Widrow, B., and Stearns, S. (1985), "Adaptive Signal Processing," Prentice-Hall, Englewood Cliffs, NJ.
-
(1985)
Adaptive Signal Processing
-
-
Widrow, B.1
Stearns, S.2
|