منابع مشابه
PAC Learning under Helpful Distributions
A PAC model under helpful distributions is introduced. A teacher associates a teaching set with each target concept and we only consider distributions such that each example in the teaching set has a non-zero weight. The performance of a learning algorithm depends on the probabilities of the examples in this teaching set. In this model, an Occam's razor theorem and its converse are proved. The ...
متن کاملPAC Classification based on PAC Estimates of Label Class Distributions
A standard approach in pattern classification is to estimate the distributions of the label classes, and then to apply the Bayes classifier to the estimates of the distributions in order to classify unlabeled examples. As one might expect, the better our estimates of the label class distributions, the better the resulting classifier will be. In this paper we make this observation precise by ide...
متن کاملLearning Shuffle Ideals Under Restricted Distributions
The class of shuffle ideals is a fundamental sub-family of regular languages. The shuffle ideal generated by a string set U is the collection of all strings containing some string u ∈ U as a (not necessarily contiguous) subsequence. In spite of its apparent simplicity, the problem of learning a shuffle ideal from given data is known to be computationally intractable. In this paper, we study the...
متن کاملLearning Simple Concept Under Simple Distributions
This is a preliminary draft version. The journal version [SIAM. J. Computing, 20:5(1991), 911935] is the correct final version. However, the polynomial time computable universal distribution section in there is too sloppy. For a better treatment see ‘‘M. Li and P.M.B. Vitanyi, An Introduction to Kolmogorov Complexity and its Applications, Springer-Verlag, New York, Second Edition, 1997,’’ Secti...
متن کاملLearning under differing training and test distributions
One of the main problems in machine learning is to train a predictive model from training data and to make predictions on test data. Most predictive models are constructed under the assumption that the training data is governed by the exact same distribution which the model will later be exposed to. In practice, control over the data collection process is often imperfect. A typical scenario is ...
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: RAIRO - Theoretical Informatics and Applications
سال: 2001
ISSN: 0988-3754,1290-385X
DOI: 10.1051/ita:2001112