Feedforward neural networks for compound signals

Authors:
Marcin Szczuka;Dominik Lzak
Affiliations:
Institute of Mathematics, The University of Warsaw, Banacha 2, 02-097 Warsaw, Poland;Institute of Mathematics, The University of Warsaw, Banacha 2, 02-097 Warsaw, Poland and Infobright Inc. Poland, Krzywickiego 34 pok. 219, 02-078 Warsaw, Poland
Venue:
Theoretical Computer Science
Year:
2011

Citing 12
Cited 0

Fuzzy neural networks: a survey

Fuzzy Sets and Systems
A learning algorithm of fuzzy neural networks with triangular fuzzy weights

Fuzzy Sets and Systems - Special issue on fuzzy neural control
On the Optimality of the Simple Bayesian Classifier under Zero-One Loss

Machine Learning - Special issue on learning with probabilistic representations
An extension of the back-propagation algorithm to complex numbers

Neural Networks
Fuzzy number neural networks

Fuzzy Sets and Systems
Neural networks for soft decision making

Fuzzy Sets and Systems - Special issue on soft decision analysis
Layered Learning in Multiagent Systems: A Winning Approach to Robotic Soccer

Layered Learning in Multiagent Systems: A Winning Approach to Robotic Soccer
Machine Learning

Machine Learning
Handbook of Granular Computing

Handbook of Granular Computing
Rough Neural Networks for Complex Concepts

RSFDGrC '07 Proceedings of the 11th International Conference on Rough Sets, Fuzzy Sets, Data Mining and Granular Computing
Rough Neuron based on Pattern Space Partitioning

Neurocomputing
A rough set-based magnetic resonance imaging partial volume detection system

PReMI'05 Proceedings of the First international conference on Pattern Recognition and Machine Intelligence

Quantified Score

Hi-index	5.23

Visualization

Abstract

In this paper we consider possible extensions of the classical multilayer artificial neural network model to the situation when the signals processed by the network are by definition compound and possibly structured. We discuss existing approaches to this problem in various contexts and provide our own model-the Normalizing Neural Network-for networks that process vectors as signals. We discuss possible uses of the proposed approach in a series of case studies.