A Bounded Neural Network for Open Set Recognition

• Type: Article in International Conference Proceedings Book
• Date: 2015

Authors

Cardoso, DO (Author) Other; Franca, F (Author) Other; João Gama (Author) FEP

Conference proceedings International

Title: 2015 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN)

Pages: 1-7

International Joint Conference on Neural Networks (IJCNN)

Killarney, IRELAND, JUL 12-17, 2015

Indexing

ISI Web of Knowledge - 22 Citations

Scopus - 27 Citations

Other information

Authenticus ID: P-00G-SYS

DOI: 10.1109/ijcnn.2015.7280680

Abstract (EN): Open set recognition is, more than an interesting research subject, a component of various machine learning applications which is sometimes neglected: it is not unusual the existence of learning systems developed on the top of closed-set assumptions, ignoring the error risk involved in a prediction. This risk is strictly related to the location in feature space where the prediction has to be made, compared to the location of the training data: the more distant the training observations are, less is known, higher is the risk. Proper handling of this risk can be necessary in various situation where classification and its variants are employed. This paper presents an approach to open set recognition based on an elaborate distance-like computation provided by a weightless neural network model. The results obtained in the proposed test scenarios are quite interesting, placing the proposed method among the current best ones.

Language: English

Type (Professor's evaluation): Scientific

No. of pages: 7