资源分类
》 资源 》论文》Bounds for Learning from Evolutionary-Related Data in the Realizable Case

Bounds for Learning from Evolutionary-Related Data in the Realizable Case

2019-11-22 | |  50 |   37 |   0
Abstract This paper deals with the generalization ability of classifiers trained from non-iid evolutionary-related data in which all training and testing examples correspond to leaves of a phylogenetic tree. For the realizable case, we prove PAC-type upper and lower bounds based on symmetries and matchings in such trees.

上一篇：Constructing Abstraction Hierarchies Using a Skill-Symbol Loop

下一篇：Learning Multi-Step Predictive State Representations

用户评价
全部评价

热门资源

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • The Variational S...

    Unlike traditional images which do not offer in...

  • A Mathematical Mo...

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

  • Rating-Boosted La...

    The performance of a recommendation system reli...