TAILIEUCHUNG - Neural network induction graph for pattern recognition

Neural network induction graph for pattern recognition | ELSEVIER Available online at Neurocomputing 57 2004 257-274 Neurocomputing locate neucom Neural network induction graph for pattern recognition O. Lezoraya D. Fournierb H. Cardotc aIUT Dept. SRC LUSAC EA 2607 120 Rue de l exode Saint-Lo F-50000 France bLIH EA 3219 25 rue Philippe Lebon . 540 Le Havre F-76058 France cDept. Informatique Polytech Tours LI EA 2101 64 Avenue Jean Portalis Tours F-37200 France Received 31 August 2001 received in revised form 14 May 2003 accepted 20 October 2003 Abstract This paper presents a novel architecture of neural networks designed for pattern recognition. The concept of induction graphs coupled with a divide-and-conquer strategy defines a neural network induction graph NNIG . First the NNIG concept is described and its properties detailed. It is based on a set of several little neural networks each one discriminating only two classes. The specialization of each neural network simplifies their structure and improves the classification. The principle used to perform the decision of classification on an input pattern is explained. The latter enables to take into account dubious decisions identified by the NNIG. The last section presents experimental results. A significant gain in the global classification rate can be obtained by using an NNIG. The discussion is illustrated by tests on databases from the UCI machine learning database repository. The experimental results show that an NNIG can achieve a better learning simpler neural networks and an improved performance in classification. A final illustration is presented on a real microscopical imaging problem for the classification of cells in serous cytology. 2003 Elsevier . All rights reserved. PACS Keywords Induction graphs Neural networks Dubious decisions Corresponding author. Tel. 33- 0 -233775517 fax 33- 0 -233771167. E-mail addresses O. Lezoray .

TỪ KHÓA LIÊN QUAN
TÀI LIỆU MỚI ĐĂNG
34    211    1    17-04-2024
10    155    0    17-04-2024
23    152    0    17-04-2024
37    153    0    17-04-2024
37    136    0    17-04-2024
10    114    0    17-04-2024
Đã phát hiện trình chặn quảng cáo AdBlock
Trang web này phụ thuộc vào doanh thu từ số lần hiển thị quảng cáo để tồn tại. Vui lòng tắt trình chặn quảng cáo của bạn hoặc tạm dừng tính năng chặn quảng cáo cho trang web này.