论文信息 - Capabilities of probabilistic learners with bounded mind changes

Capabilities of probabilistic learners with bounded mind changes

We consider the power of randomization in finite learning when a bounded number of mind changes are allowed. We show that in the ~m+2_3 range ( ~~+a _2, 1] the capability type of probabilistic as well as pluralistic FIN-type (also PFIN-type) learners is defined by the sequence

Bala Kalyanasundaram | Robert P. Daley

[1] Bala Kalyanasundaram,et al. The power of probabilism in Popperian FINite learning , 1994, J. Exp. Theor. Artif. Intell..

[2] Arun Sharma,et al. Finite learning by a “team” , 1990, COLT '90.

[3] Carl H. Smith,et al. The Power of Pluralism for Automatic Program Synthesis , 1982, JACM.

[4] Leonard Pitt,et al. Probabilistic inductive inference , 1989, JACM.

[5] Bala Kalyanasundaram,et al. The Power of Probabilism in Popperian FINite Learning (extended abstract) , 1992, AII.

[6] Carl H. Smith,et al. Probability and Plurality for Aggregations of Learning Machines , 1987, Inf. Comput..

[7] Bala Kalyanasundaram,et al. Probabilistic and Pluralistic Learners with Mind Changes , 1992, MFCS.

[8] Rusins Freivalds,et al. On the Power of Probabilistic Strategies in Inductive Inference , 1984, Theor. Comput. Sci..

[9] Bala Kalyanasundaram,et al. Breaking the probability ½ barrier in FIN-type learning , 1992, COLT '92.

[10] E. Mark Gold,et al. Language Identification in the Limit , 1967, Inf. Control..

[11] Leonard Pitt,et al. Relations between probabilistic and team one-shot learners (extended abstract) , 1991, COLT '91.

[12] Mahendran Velauthapillai. Inductive inference with bounded number of mind changes , 1989, COLT '89.