论文信息 - Inductive Inference with Procrastination: Back to Definitions

Inductive Inference with Procrastination: Back to Definitions

In this paper, we reconsider the definition of procrastinating learning machines. In the original definition of Freivalds and Smith [FS93], constructive ordinals are used to bound mindchanges. We investigate possibility of using arbitrary linearly ordered sets to bound mindchanges in similar way. It turns out that using certain ordered sets it is possible to define inductive inference types different from the previously known ones. We investigate properties of the new inductive inference types and compare them to other types.

[1] A. Church. The constructive second number class , 1938 .

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

[3] Carl H. Smith,et al. On the Role of Procrastination in Machine Learning , 1993, Inf. Comput..

[4] Carl H. Smith,et al. Inductive Inference: Theory and Methods , 1983, CSUR.

[5] Kalvis Apsitis. Derived Sets and Inductive Inference , 1994, AII/ALT.

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

[7] Arun Sharma,et al. Elementary formal systems, intrinsic complexity, and procrastination , 1997, COLT '96.

[8] Carl H. Smith,et al. General Inductive Inference Types Based on Linearly-Ordered Sets , 1996, STACS.

[9] John Case,et al. Not-So-Nearly-Minimal-Size Program Inference , 1995, GOSLER Final Report.

[10] Stephen Cole Kleene,et al. On notation for ordinal numbers , 1938, Journal of Symbolic Logic.

[11] Andris Ambainis. The power of procrastination in inductive inference: How it depends on used ordinal notations , 1995, EuroCOLT.

[12] Alonzo Church,et al. Formal definitions in the theory of ordinal numbers , 1937 .

[13] Arun Sharma,et al. Generalized notions of mind change complexity , 1997, COLT '97.