The following information was submitted:
Transactions: INTERNATIONAL JOURNAL of CIRCUITS, SYSTEMS and SIGNAL PROCESSING
Transactions ID Number: 19-202
Full Name: Fernando Morgado Dias
Position: Professor
Age: ON
Sex: Male
Address: CCCEE, Campus da Penteada, Universidade da Madeira
Country: PORTUGAL
Tel:
Tel prefix:
Fax:
E-mail address: morgado@uma.pt
Other E-mails: morgado_dias@clix.pt
Title of the Paper: Fault Tolerance of Artificial Neural Networks: Open Discussion for a Global Model
Authors as they appear in the Paper: Fernando Morgado Dias and Ana Antunes
Email addresses of all the authors: morgado@uma.pt,aantunes@est.ips.pt
Number of paper pages: 8
Abstract: It is commonly assumed that neural networks have a built in fault tolerance property mainly due to their parallel structures. The international community of Neural Networks discussed these properties only until 1994 and afterwards the subject has been mostly ignored. Recently the subject was again brought to discussion due to the possibility of using neural networks in nano-electronic systems where fault tolerance and graceful degradation properties would be very important. In spite of these two periods of work there is still need for a large discussion around the fault model for artificial neural networks that should be used. One of the most used models is based on the stuck at model but applied to the weights. This model does not cover all possible faults and a more general model should be found. The present paper proposes a model for the faults in hardware implementations of feedforward neural networks that is independent of the implementation chosen and covers !
more faults than all the models proposed before in the literature.
Keywords: Feedforward neural networks, Hardware implementation, Fault tolerance, Fault model, Fault coverage, Graceful degradation
EXTENSION of the file: .doc
Special (Invited) Session: A global model for fault tolerance of feedforward neural networks
Organizer of the Session: 589-479
How Did you learn about congress:
IP ADDRESS: 193.136.232.2
