The power of probabilism in Popperian FINite learning

Abstract We consider the capabilities of probabilistic and team learners who (a) are allowed to conjecture only one hypothesis when given a function to learn; and (b) must always produce a program (i.e. hypotheses) that halts on every input. Learners satisfying only (a) are termed FIN-type learners, and learners satisfying both (a) and (b) are termed PFIN-type learners. We show that the structure of the learning capability of probabilistic and team learning with success ratio above 1/2 in PFIN-type learning is analogous to the structure observed in FIN-type learning. On the contrary, the structure of probabilistic and team learning with success ratio below 1/2 is more sparse for PFIN-type learning than for FIN-type learning. For n ≥ 2, we show that the probabilistic hierarchy below 1/2 for PFIN-type learning is denned by the sequence 4n/(9n − 2), which has an accumulation point at 4/9. We also show that the redundancy type at the accumulation point 4/9 is different from the one observed at 1/2. More inter...

[1]  Carl H. Smith,et al.  Probability and Plurality for Aggregations of Learning Machines , 1988, Inf. Comput..

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

[3]  Robert P. Daley.  On the Error Correcting Power of Pluralism in Inductive Inference , 1981, FCT.

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

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

[6]  John Case,et al.  Comparison of Identification Criteria for Machine Inductive Inference , 1983, Theor. Comput. Sci..

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

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

[9]  Bala Kalyanasundaram,et al.  Use of Reduction Arguments in Determining Popperian FIN-Type Learning Capabilities , 1993, ALT.

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

[13]  Daniel N. Osherson,et al.  Systems That Learn: An Introduction to Learning Theory for Cognitive and Computer Scientists , 1990 .

[14]  Bala Kalyanasundaram,et al.  Capabilities of probabilistic learners with bounded mind changes , 1993, COLT '93.