资源分类
》 资源 》论文》Online Learning of k-CNF Boolean Functions

Online Learning of k-CNF Boolean Functions

2019-11-20 | |  65 |   41 |   0
Abstract This paper revisits the problem of learning a k-CNF Boolean function from examples, for fixed k, in the context of online learning under the logarithmic loss. We give a Bayesian interpretation to one of Valiant’s classic PAC learning algorithms, which we then build upon to derive three efficient, online, probabilistic, supervised learning algorithms for predicting the output of an unknown k-CNF Boolean function. We analyze the loss of our methods, and show that the cumulative log-loss can be upper bounded by a polynomial function of the size of each example.

上一篇：Portable Option Discovery for Automated Learning Transfer in Object-Oriented Markov Decision Processes

下一篇：Feature Selection from Microarray Data via an Ordered Search with Projected Margin

用户评价
全部评价

热门资源

  • The Variational S...

    Unlike traditional images which do not offer in...

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...

  • Rating-Boosted La...

    The performance of a recommendation system reli...