Overview
- Editors:
-
-
Barbara Hammer
-
University Clausthal, Germany
-
Pascal Hitzler
-
University of Karlsruhe, Germany
- Presents recent developments in neural-symbolic integration
Access this book
Other ways to access
Table of contents (12 chapters)
-
Front Matter
Pages I-XIII
-
Structured Data and Neural Networks
-
-
- Craig Saunders, Anthony Demco
Pages 7-22
-
- Fabrizio Costa, Sauro Menchetti, Paolo Frasconi
Pages 23-48
-
- Tayfun Gürel, Luc De Raedt, Stefan Rotter
Pages 49-65
-
- Barbara Hammer, Alessio Micheli, Alessandro Sperduti
Pages 67-94
-
- Peter Tiňo, Barbara Hammer, Mikael Bodén
Pages 95-133
-
-
- Helge Ritter, Robert Haschke, Jochen J. Steil
Pages 159-178
-
Logic and Neural Networks
-
Front Matter
Pages 179-182
-
-
- Sebastian Bader, Pascal Hitzler, Steffen Hölldobler, Andreas Witzel
Pages 205-232
-
- Helmar Gust, Kai-Uwe Kühnberger, Peter Geibel
Pages 233-264
-
-
- Ekaterina Komendantskaya, Máire Lane, Anthony Karel Seda
Pages 283-313
-
Back Matter
Pages 315-319
About this book
The human brain possesses the remarkable capability of understanding, - terpreting, and producing human language, thereby relying mostly on the left hemisphere. The ability to acquire language is innate as can be seen from d- orders such as speci?c language impairment (SLI), which manifests itself in a missing sense for grammaticality. Language exhibits strong compositionality and structure. Hence biological neural networks are naturally connected to processing and generation of high-level symbolic structures. Unlike their biological counterparts, arti?cial neural networks and logic do not form such a close liason. Symbolic inference mechanisms and statistical machine learning constitute two major and very di?erent paradigms in ar- ?cial intelligence which both have their strengths and weaknesses: Statistical methods o?er ?exible and highly e?ective tools which are ideally suited for possibly corrupted or noisy data, high uncertainty and missing information as occur in everyday life such as sensor streams in robotics, measurements in medicine such as EEG and EKG, ?nancial and market indices, etc. The m- els, however, are often reduced to black box mechanisms which complicate the integration of prior high level knowledge or human inspection, and they lack theabilitytocopewitharichstructureofobjects,classes,andrelations. S- bolic mechanisms, on the other hand, are perfectly applicative for intuitive human-machine interaction, the integration of complex prior knowledge, and well founded recursive inference. Their capability of dealing with uncertainty andnoiseandtheire?ciencywhenaddressingcorruptedlargescalereal-world data sets, however, is limited. Thus, the inherent strengths and weaknesses of these two methods ideally complement each other.
Editors and Affiliations
-
University Clausthal, Germany
Barbara Hammer
-
University of Karlsruhe, Germany
Pascal Hitzler
