A Parameterization Scheme for Classifying Models of PAC Learnability
نویسندگان
چکیده
منابع مشابه
The PAC - learnability of Planning
In 6] Natarajan presented a framework for the speedup learning of search algorithms. Speedup learning solves the problem of using teacher-provided examples to guide the improvement of algorithm eeciency. In this paper we extend their results by identifying two classes, the emonomial and emonotonic domains. We show that, in the Natarajan model, the speedup learning problem is solvable for the se...
متن کاملa study on thermodynamic models for simulation of 1,3 butadiene purification columns
attempts have been made to study the thermodynamic behavior of 1,3 butadiene purification columns with the aim of retrofitting those columns to more energy efficient separation schemes. 1,3 butadiene is purified in two columns in series through being separated from methyl acetylene and 1,2 butadiene in the first and second column respectively. comparisons have been made among different therm...
Characterizing PAC-Learnability of Semilinear Sets
The learnability of the class of letter-counts of regular languages (semilinear sets) and other related classes of subsets of N d with respect to the distribution-free learning model of Valiant (PAC-learning model) is characterized. Using the notion of reducibility among learning problems due to Pitt and Warmuth called \prediction preserving reducibility," and a special case thereof, a number o...
متن کاملThe Pac-Learnability of Recursive Logic Programs
We analyze the learnability of function-free recursive logic programs in the models of polynomial predictability and identiication from equivalence queries. Our ultimate goal is delineating the boundaries of eecient learnability for recursive logic programs. In the rst portion of the paper, we describe a restricted class of recursive programs that is learnable from equivalence queries alone. Th...
متن کاملThe Passive Student Is Really Weaker (a Parametrization Scheme for Classifying Models'of Learnability)
Abslract We present a systematic framework: for classifying, comparing and defining models of computadonalleamabili1y. Apart from the obvious 'uniformity' parameters we present a novel 'passiveness' notion that captures the difference between 'Guess and Test' learning algorithms and leamability notions for which consistency with the samples guaranlU3 success. We analyze known models in terms of...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Information and Computation
سال: 1995
ISSN: 0890-5401
DOI: 10.1006/inco.1995.1094