Multimodal Information Architecture: contribution on Artificial Intelligence developments

Abstract

1 informational space to be used in neural network training and learning methods, in order to complement gaps identified by authors focused on computer science implementations. Great potential for developing a structured method of Multimodal Information Architecture was observed, which would provide instruments for organizing data pre-processing which are used as test and learning sample in artificial neural networks. This method could place information science as an actor and producer of artificial intelligence solutions, replacing its current role as consumer of prefabricated solutions made by computer science. To present Multimodal Information Architecture contributions on information organizing on training artificial neural networks, aiming to position information science as an active body of knowledge in artificial intelligence problems. The definitions of Multimodal Information Architecture were used following the technological phase with an explanatory and qualitative approach. A five-step procedure is proposed for delineating, analyzing and transforming the