Title :
Optimum complexity neural networks for anomaly detection task
Author :
Kozma, Robert ; Majumdar, Nivedita Sumi ; Dasgupta, Dipankar
Author_Institution :
Div. of Comput. Sci., Univ. of Memphis, TN, USA
fDate :
6/24/1905 12:00:00 AM
Abstract :
In this paper we study the performance of compressed data for classification and anomaly detection. We use networks of various complexities for our purpose, guided by the data itself rather than one uniform-complexity network for the entire data set
Keywords :
neural nets; optimisation; pattern classification; anomaly detection task; classification; compressed data; optimum complexity neural networks; uniform-complexity network; Computer science; Data compression; Degradation; Intelligent systems; Nearest neighbor searches; Neural networks; Niobium; Performance evaluation; Testing;
Conference_Titel :
Neural Networks, 2002. IJCNN '02. Proceedings of the 2002 International Joint Conference on
Conference_Location :
Honolulu, HI
Print_ISBN :
0-7803-7278-6
DOI :
10.1109/IJCNN.2002.1007654
