کد مقاله کد نشریه سال انتشار مقاله انگلیسی نسخه تمام متن
429212 687096 2007 5 صفحه PDF دانلود رایگان
عنوان انگلیسی مقاله ISI
Discriminative learning can succeed where generative learning fails
موضوعات مرتبط
مهندسی و علوم پایه مهندسی کامپیوتر نظریه محاسباتی و ریاضیات
پیش نمایش صفحه اول مقاله
Discriminative learning can succeed where generative learning fails
چکیده انگلیسی

Generative algorithms for learning classifiers use training data to separately estimate a probability model for each class. New items are classified by comparing their probabilities under these models. In contrast, discriminative learning algorithms try to find classifiers that perform well on all the training data.We show that there is a learning problem that can be solved by a discriminative learning algorithm, but not by any generative learning algorithm. This statement is formalized using a framework inspired by previous work of Goldberg [P. Goldberg, When can two unsupervised learners achieve PAC separation?, in: Proceedings of the 14th Annual COLT, 2001, pp. 303–319].

ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Information Processing Letters - Volume 103, Issue 4, 16 August 2007, Pages 131-135