A Tool for Fast Development of Modular and Hierarchic Neural Network-based Systems

• Type: Article in International Scientific Journal
• Date: 2006

Authors

Francisco Reinaldo (Author) FEUP; Mauro Roisenberg (Author) Other; Rui Camacho (Author) FEUP; Luís Reis (Author) FEUP

Journal

Title: EJIS, Electronic Journal of Information Systems

Vol. 5 No. 2

ISSN: 16773071

Scientific classification

FOS: Engineering and technology > Electrical engineering, Electronic engineering, Information engineering

CORDIS: Technological sciences > Engineering > Knowledge engineering

Other information

Abstract (EN): This paper presents PyramidNet tool as a fast and easy way to develop Modular and Hierarchic Neural Network-based Systems. This tool facilitates the fast emergence of autonomous behaviors in agents because it uses a hierarchic and modular control methodology of heterogeneous learning modules: the pyramid. Using the graphical resources of PyramidNet the user is able to specify a behavior system even having little understanding of artificial neural networks. Experimental tests have shown that a very significant speedup is attained in the development of modular and hierarchic neural network-based systems by using this tool.

Language: English

Type (Professor's evaluation): Scientific