Instance Metrics Improvement by Probabilistic Support
نویسندگان
چکیده
The use of distance functions in order to determine nearest instance class at Memory Based Learning methods may be crucial when there are no exact matchings. We add relative information over unknown feature values to improve the information extract on the training instances. An experiment was carried out for Spanish Part-Of-Speech tagging of unknown words nding a better performance with our modi-ed function.
منابع مشابه
Support vector regression with random output variable and probabilistic constraints
Support Vector Regression (SVR) solves regression problems based on the concept of Support Vector Machine (SVM). In this paper, a new model of SVR with probabilistic constraints is proposed that any of output data and bias are considered the random variables with uniform probability functions. Using the new proposed method, the optimal hyperplane regression can be obtained by solving a quadrati...
متن کاملProbabilistic Normed Groups
In this paper, we introduce the probabilistic normed groups. Among other results, we investigate the continuityof inner automorphisms of a group and the continuity of left and right shifts in probabilistic group-norm. We also study midconvex functions defined on probabilistic normed groups and give some results about locally boundedness of such functions.
متن کاملMazur-Ulam theorem in probabilistic normed groups
In this paper, we give a probabilistic counterpart of Mazur-Ulam theorem in probabilistic normed groups. We show, under some conditions, that every surjective isometry between two probabilistic normed groups is a homomorphism.
متن کاملAchievable Rates for Probabilistic Shaping
For a layered probabilistic shaping (PS) scheme with a general decoding metric, an achievable rate is derived using Gallager’s error exponent approach. Several instances for specific decoding metrics are discussed, including bit-metric decoding, interleaved coded modulation, and hard-decision decoding. It is shown that important previously known achievable rates can also be achieved by layered ...
متن کاملEvaluation of Classifiers in Software Fault-Proneness Prediction
Reliability of software counts on its fault-prone modules. This means that the less software consists of fault-prone units the more we may trust it. Therefore, if we are able to predict the number of fault-prone modules of software, it will be possible to judge the software reliability. In predicting software fault-prone modules, one of the contributing features is software metric by which one ...
متن کامل