作 者 详细资料 mengyang1983 的文献笔记 订阅 |
This enables an appropriate training of both ordinary and structural parameters of the model. Note that the preference towards high entropy distributions (fewer assumptions) applies only within the admissible set of distributions P'"Y consistent with the constraints. |
Information-Theoretic Dictionary Learning for Image Classification
Learning Discriminative and Shareable Features
for Scene ClassificationUnsupervised feature learning by deep sparse codingLearning Euclidean-to-Riemannian Metric for Point-to-Set ClassificationLow-rank Matrix Recovery via Iteratively Reweighted Least Squares Minimization
浙公网安备 33010202000686号 ( 浙ICP备09035230号-1 )
