• Plataforma de vídeos del IIT
  • Twitter
  • LinkedIn
  • Asociación de Ingenieros del ICAI
  • Intranet
  • Spanish
Go top
Conference paper information

Real Time Dynamic Ellipsoidal Neural Network (RTDENN)

A. Sánchez, M.A. Sanz-Bobi

2002 WSEAS Int. Conf. on Signal Processing, Robotics and Automation (ISPRA '02), Cadiz (Spain). 12 June 2002


Summary:
This paper describes a new neural network able to adapt itself, both its parameters and its structure, to a data set in real-time conditions. The adaptation is based on a non-supervised learning procedure. The new neural network can automatically create interconnections between neurons using a Gaussian activation function. Still another important feature of this new neural network is the use of few neurons to make a good prediction using a reduced number of examples. This is relevant in order to make fast calculations using few resources in real-time applications. Some examples focusing on mobile robotics applications are included in order to demonstrate its good performance.


Keywords: one-pass learning, neural networks, environment modeling, real-time navigation, autonomous, mobile robot.


Publication date: June 2002.



Citation:
A. Sánchez, M.A. Sanz-Bobi, Real Time Dynamic Ellipsoidal Neural Network (RTDENN), 2002 WSEAS Int. Conf. on Signal Processing, Robotics and Automation (ISPRA '02), Cadiz (Spain). 12-16 June 2002.


    Research topics:
  • *Mobile Robots and artificial vision

IIT-02-036A

Request Request the document to be emailed to you.