Abstract
In the past decade there has been a big effort in implementing automatic systems that can be used in most environments and are able to decrease human work and therefore, human errors. Most of these systems are devoted to applications where the problem faced cannot be clearly described by a set of finite steps (algorithmically), and, in the cases when it can described algorithmically, the computational complexity required to perform one or more of the steps is prohibitive. Those problems, in computer science language are called NP-complete and NP-hard problems, where NP indicates that the problem has a Non Polynomial solution either in terms of computational time or in terms of memory occupancy, or both.
This work has been supported by NSF KDI program, Grant No. BCS-9980054 “Cross modal analysis of speech signal and sense: multimedia corpora and tools for gesture, speech, and gaze research” and by NSF Grant No. 9906340 “Speech driven facial animation”.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2002 Springer Science+Business Media New York
About this chapter
Cite this chapter
Esposito, A. (2002). The Importance of Data for Training Intelligent Devices. In: Apolloni, B., Kurfess, F. (eds) From Synapses to Rules. Springer, Boston, MA. https://doi.org/10.1007/978-1-4615-0705-5_12
Download citation
DOI: https://doi.org/10.1007/978-1-4615-0705-5_12
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4613-5204-4
Online ISBN: 978-1-4615-0705-5
eBook Packages: Springer Book Archive