Direct and Indirect Algorithms for On-line Learning of Disjunctions
نویسندگان
چکیده
It is easy to design on-line learning algorithms for learning k out of n variable monotone disjunctions by simply keeping one weight per disjunction. Such algorithms use roughly O(n) weights which can be prohibitively expensive. Surprisingly, algorithms like Winnow require only n weights (one per variable) and the mistake bound of these algorithms is not too much worse than the mistake bound of the more costly algorithms. The purpose of this paper is to investigate how the exponentially many weights can be collapsed into only O(n) weights. In particular, we consider probabilistic assumptions that enable the Bayes optimal algorithm’s posterior over the disjunctions to be encoded with only O(n) weights. This results in a new O(n) algorithm for learning disjunctions which is related to the Bylander’s BEG algorithm originally introduced for linear regression. Beside providing a Bayesian interpretation for this new algorithm, we are also able to obtain mistake bounds for the noise free case resembling those that have been derived for the Winnow algorithm. The same techniques used to derive this new algorithm also provide a Bayesian interpretation for a normalized version of Winnow.
منابع مشابه
The Position of Implicit and Indirect Learning in Ethical Education
The rationalist approach has been dominated on the education environment of values for many years. Unilateral and excessive focus on this approach has revealed ignorance of a vast part of human implicit learning and his intuitive ethical judgments which have been the source of many ethical behaviors. The study intends to answer the question that why only direct and deductive educations about va...
متن کاملThe Comparative Effect of Direct and Indirect Corrective Feedback in Process-Based Vs. Product-Based Writing Instruction on EFL Learners` Writing Performance
This study attempted to systematically inspect the impact of direct and indirect corrective feedbacks on the writing ability of EFL learners when using product/process based instructions. To do so, 110 female EFL learners, between the ages of 15 and 18, were randomly assigned into four experimental groups to receive four different kinds of treatments, namely product-based instruction with direc...
متن کاملOn the Applicability of Oxford's Taxonomy of Learner Strategies to Translation Tasks
During the last three decades, especially 1980's, language learning specialists have been busy discovering the nature of language learning strategies, describing them, and formulating their relationships with other language learning factors. In line with these studies, the field of translation studies has undergone a complete revolution in terms of its perspective toward its research prioritie...
متن کاملThe Relationship between Social Capital and the Mediating Role of Social Learning with Rangerss' Satisfaction with Plans in Mazandaran Summer Rangelands
Background and purpose: The future of human life depends on a better understanding of the factors that lead to satisfaction. Social capital is one of the factors that can grow through the exchange of knowledge and experience and communication with others and be effective in promoting the satisfaction of local communities. Effective and efficient implementation of rangeland rehabilitation progra...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 1999