图 书 馆开课单位--希伯来大学
1 1/1
1Future Information Minimization as PAC Bayes regularization in Reinforcement Learning[未来信息最小化为PAC贝叶斯正则化的强化学习]
Naftali Tishby(希伯来大学) Interactions between an organism and its environment are commonly treated in the framework of Markov Decision Processes (MDP). While standard MDP is a...
热度：63
Naftali Tishby(希伯来大学) Interactions between an organism and its environment are commonly treated in the framework of Markov Decision Processes (MDP). While standard MDP is a...
热度：63
2How to discount Information: Information flow in sensing-acting systems and the emergence of heirarchies[如何对信息进行折扣：传感代理系统中的信息流与体系结构的出现]
Naftali Tishby(希伯来大学) We argue that consistent formulation of optimal sensing and control must include information terms, yielding an extension of the standard POMDP settin...
热度：61
Naftali Tishby(希伯来大学) We argue that consistent formulation of optimal sensing and control must include information terms, yielding an extension of the standard POMDP settin...
热度：61
3Multiclass Learnability and the ERM principle[多类学习能力与经验风险最小化]
Amit Daniely(希伯来大学) Multiclass learning is an area of growing practical relevance, for which the currently available theory is still far from providing satisfactory under...
热度：65
Amit Daniely(希伯来大学) Multiclass learning is an area of growing practical relevance, for which the currently available theory is still far from providing satisfactory under...
热度：65
1 1/1