• Title Recurrent Neural Networks for Temporal Data Processing
• Author(s) Hubert Cardot
• Publisher: IN-TECH (February 2011); eBook (Creative Commons Licensed)
• License(s): Attribution 3.0 Unported (CC BY 3.0)
• Hardcover 108 pages
• Language: English
• ISBN-10: N/A
• ISBN-13: 978-953-307-685-0
• Share This:  

Book Description

By presenting the latest research work the book demonstrates how real-time recurrent neural networks (RNNs) can be implemented to expand the range of traditional signal processing techniques and to help combat the problem of prediction. Within this text neural networks are considered as massively interconnected nonlinear adaptive filters.

The RNNs (Recurrent Neural Networks) are a general case of artificial neural networks where the connections are not feed-forward ones only. In RNNs, connections between units form directed cycles, providing an implicit internal memory. Those RNNs are adapted to problems dealing with signals evolving through time. Their internal memory gives them the ability to naturally take time into account. Valuable approximation results have been obtained for dynamical systems.

• H. Cardot is a full professor at the University François Rabelais Tours in France since 2003. He received his PhD in 1993 from the University of Caen (France). He is head of the Pattern Recognition and Image Analysis group (20 researchers) of the LI research laboratory. His research focuses on pattern recognition and in particular neural networks and SVM for time series prediction. He teaches at the Engineers Polytechnic School of Tours.

• Amazon

• Neural Networks and Deep Learning
• Machine Learning
• Artificial Intelligence

• Recurrent Neural Networks for Temporal Data Processing (Hubert Cardot)
• PDF Format

• Recurrent Neural Networks and Soft Computing (M. ElHefnawi)
• Recurrent Neural Networks (Xiaolin Hu, et al)
• Applied Artificial Neural Networks (Christian Dawson)
• Artificial Neural Networks - Architectures and Applications (Kenji Suzuki)