开课单位--INRIA研究机构
21
Prediction by random-walk perturbation[随机游走扰动预测]
Gergely Neu(INRIA研究机构) We propose a version of the follow-the-perturbed-leader online prediction algorithm in which the cumulative losses are perturbed by independent symmet...
热度:56
Gergely Neu(INRIA研究机构) We propose a version of the follow-the-perturbed-leader online prediction algorithm in which the cumulative losses are perturbed by independent symmet...
热度:56
22
Machine learning and kernel methods for computer vision[计算机视觉的机器学习与核方法]
Francis R. Bach(INRIA研究机构) Kernel methods are a new theoretical and algorithmic framework for machine learning. By representing data through well defined dot-products, referred ...
热度:33
Francis R. Bach(INRIA研究机构) Kernel methods are a new theoretical and algorithmic framework for machine learning. By representing data through well defined dot-products, referred ...
热度:33
23
Non-Asymptotic Analysis of Stochastic Approximation Algorithms for Machine Learning[机器学习的随机逼近算法的非渐近分析]
Francis R. Bach(INRIA研究机构) We consider the minimization of a convex objective function defined on a Hilbert space, which is only available through unbiased estimates of its grad...
热度:77
Francis R. Bach(INRIA研究机构) We consider the minimization of a convex objective function defined on a Hilbert space, which is only available through unbiased estimates of its grad...
热度:77
24
Developmental constraints on active learning for the acquisition of motor skills in high-dimensional robots[对高维机器人运动技能的习得在主动学习发展的制约因素]
Pierre-Yves Oudeyer(INRIA研究机构) 在机器人运动控制的学习,如学习视觉达到或对象操作的人形机器人,是在“传统”的机器人和机器人技术的发展的一个核心话题。一个主要的障碍是,学习可...
热度:58
Pierre-Yves Oudeyer(INRIA研究机构) 在机器人运动控制的学习,如学习视觉达到或对象操作的人形机器人,是在“传统”的机器人和机器人技术的发展的一个核心话题。一个主要的障碍是,学习可...
热度:58
25