کد مقاله | کد نشریه | سال انتشار | مقاله انگلیسی | نسخه تمام متن |
---|---|---|---|---|
10361219 | 870041 | 2005 | 14 صفحه PDF | دانلود رایگان |
عنوان انگلیسی مقاله ISI
Reinforcement learning combined with a fuzzy adaptive learning control network (FALCON-R) for pattern classification
دانلود مقاله + سفارش ترجمه
دانلود مقاله ISI انگلیسی
رایگان برای ایرانیان
کلمات کلیدی
Performance evaluation - ارزیابی یا سنجش عملکردDynamic programming - برنامهریزی پویا یا برنامه نویسی پویاNoise tolerance - تحمل صداdisturbance rejection - رد دلبستگیClassification system - سیستم طبقه بندیfuzzy rules - قوانین فازیLocal minima - مینیمم های محلیReinforcement learning - یادگیری تقویتی
موضوعات مرتبط
مهندسی و علوم پایه
مهندسی کامپیوتر
چشم انداز کامپیوتر و تشخیص الگو
پیش نمایش صفحه اول مقاله
چکیده انگلیسی
Reinforcement learning has been widely-used for applications in planning, control, and decision making. Rather than using instructive feedback as in supervised learning, reinforcement learning makes use of evaluative feedback to guide the learning process. In this paper, we formulate a pattern classification problem as a reinforcement learning problem. The problem is realized with a temporal difference method in a FALCON-R network. FALCON-R is constructed by integrating two basic FALCON-ART networks as function approximators, where one acts as a critic network (fuzzy predictor) and the other as an action network (fuzzy controller). This paper serves as a guideline in formulating a classification problem as a reinforcement learning problem using FALCON-R. The strengths of applying the reinforcement learning method to the pattern classification application are demonstrated. We show that such a system can converge faster, is able to escape from local minima, and has excellent disturbance rejection capability.
ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Pattern Recognition - Volume 38, Issue 4, April 2005, Pages 513-526
Journal: Pattern Recognition - Volume 38, Issue 4, April 2005, Pages 513-526
نویسندگان
K.H. Quah, C. Quek, G. Leedham,