Reinforcement Learning (RL) algorithms work well with well-defined rewards, but they fail sparse/deceptive rewards and require additional exploration strategies. This introduces a deep method based on the Upper Confidence Bound (UCB) bonus. The proposed can be plugged into actor-critic that use neural networks as critic. Based conclusion of regret bound under linear Markov decision process appr...

We propose a general approach to discriminant feature extraction and fusion, built on an optimal feature transformation for discriminant analysis [6]. Our experiments indicate that our approach can dramatically reduce the dimensionality of original feature space whilst improving its discriminant power. Our feature fusion method can be carried out in the reduced lowerdimensional subspace, result...

Ranked transformations should preserve a priori given ranked relations (order) between some feature vectors. Designing ranked models includes feature selection tasks. Components of feature vectors which are not important for preserving the vectors order should be neglected. This way unimportant dimensions are greatly reduced in the feature space. It is particularly important in the case of “lon...

A nonlinear feature extraction method is presented which can reduce the data dimension down to the number of clusters, providing dramatic savings in computational costs. The dimension reducing nonlinear transformation is obtained by implicitly mapping the input data into a feature space using a kernel function, and then finding a linear mapping based on an orthonormal basis of centroids in the ...

In this chapter, we give a comprehensive overview on high-dimensional classification, which is prominently featured in many contemporary statistical problems. Emphasis is given on the impact of dimensionality on implementation and statistical performance and on the feature selection to enhance statistical performance as well as scientific understanding between collected variables and the outcom...

as regards of supper efficiency models which increased thediscrimination power of the standard dea models, still infeasibility mayoccure. in literature there exists some models overcome this difficulty.in this paper a new procedure has been mooted in order to remove thisshortcoming in a way that both input savings and output surplus arebeing considered. this procedure deals with nonradial chang...