The following information was submitted:
Transactions: WSEAS TRANSACTIONS ON CIRCUITS AND SYSTEMS
Transactions ID Number: 29-485
Full Name: Valentina Emilia Balas
Position: Associate Professor
Age: ON
Sex: Female
Address: B-dul Revolutiei nr. 77, Arad
Country: ROMANIA
Tel: +40-740-059151
Tel prefix:
Fax: +40-257-250389
E-mail address: balas@inext.ro
Other E-mails: valentinabalas@yahoo.com
Title of the Paper: Multilayer Perceptron and Neural Networks
Authors as they appear in the Paper: Marius-Constantin Popescu, Valentina E. Balas, Liliana Petrescu-Popescu, Nikos Mastorakis
Email addresses of all the authors: popescu.marius.c@gmail.com, balas@inext.ro, mastor@wses.org
Number of paper pages: 10
Abstract: The attempts for solving linear inseparable problems have led to different variations on the number of layers of neurons and activation functions used. The backpropagation algorithm is the most known and used supervised learning algorithm. Also called the generalized delta algorithm because it expands the training way of the adaline network, it is based on minimizing the difference between the desired output and the actual output, through the downward gradient method (the gradient tells us how a function varies in different directions). Training a multilayer perceptron is often quite slow, requiring thousands or tens of thousands of epochs for complex problems. The best known methods to accelerate learning are: the momentum method and applying a variable learning rate. The paper presents the possibility to control the induction driving using neural systems.
Keywords: Representation equations, Control, Null controllability, Air conditioning
EXTENSION of the file: .doc
Special (Invited) Session: The Backpropagation Algorithm Functions for the Multilayer Perceptron
Organizer of the Session: ID 622-083
How Did you learn about congress:
IP ADDRESS: 92.85.172.224
