Error reduction through learning multiple descriptions
نویسندگان
چکیده
منابع مشابه
Multiple Descriptions , Error Concealment , and Re ned Descriptions for Image
{ This paper demonstrates the conservative nature of a multiple description approach to image and video coding, by showing that error con-cealment of a sub-optimally partitioned coded image stream yields comparable results under realistic conditions. Rather than use the non-orthogonal transforms of multiple description coding, which result in excess rate when both streams are received, a standa...
متن کاملToward Optimal Active Learning through Sampling Estimation of Error Reduction
This paper presents an active learning method that directly optimizes expected future error. This is in contrast to many other popular techniques that instead aim to reduce version space size. These other methods are popular because for many learning models, closed form calculation of the expected future error is intractable. Our approach is made feasible by taking a sampling approach to estima...
متن کاملOn Learning Multiple Descriptions of a Concept
In sparse data environments, greater classi cation accuracy can be achieved by learning several concept descriptions of the data and combining their classi cations. Stochastic search is a general tool which can be used to generate many good concept descriptions (rule sets) for each class in the data. Bayesian probability theory o ers an optimal strategy for combining classi cations of the indiv...
متن کاملToward Optimal Active Learning through Monte Carlo Estimation of Error Reduction
This paper presents an active learning method that directly optimizes expected future error. This is in contrast to many other popular techniques that instead aim to reduce version space size. These methods are popular because for many learning models, closed form calculation of the expected future error is intractable. Our approach is made feasible by taking a Monte Carlo approach to estimatin...
متن کاملHydra-mm: Learning Multiple Descriptions to Improve Classification Accuracy
For learning tasks with few examples, greater classi cation accuracy can be achieved by learning several concept descriptions for each class in the data and producing a classi cation that combines evidence from multiple descriptions. Stochastic (randomized) search can be used to generate many concept descriptions for each class. Here we use a tractable approximation to the optimal Bayesian meth...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Machine Learning
سال: 1996
ISSN: 0885-6125,1573-0565
DOI: 10.1007/bf00058611