Perspectives of neural-symbolic integration
The human brain possesses the remarkable capability of understanding, interpreting, and producing language, structures, and logic. Unlike their biological counterparts, artificial neural networks do not form such a close liason with symbolic reasoning: logic-based inference mechanisms and statistical machine learning constitute two major and very different paradigms in artificial intelligence with complementary strengths and weaknesses. Modern application scenarios in robotics, bioinformatics, language processing, etc., however require both the efficiency and noise-tolerance of statistical models and the generalization ability and high-level modelling of structural inference meachanisms. A variety of approaches has therefore been proposed for combining the two paradigms. This carefully edited volume contains state-of-the-art contributions in neural-symbolic integration, covering `loose' coupling by means of structure kernels or recursive models as well as `strong' coupling of logic and neural networks. It brings together a representative selection of results presented by some of the top researchers in the field, covering theoretical foundations, algorithmic design, and state-of-the-art applications in robotics and bioinformatics
1 online resource (xiii, 319 pages) : illustrations
9783540739548, 9783540739531, 9781281043597, 9786611043599, 3540739548, 354073953X, 1281043591, 6611043594
261225117
Kernels for strings and graphs / Craig Saunders and Anthony Demco
Comparing sequence classification algorithms for protein subcellular localization / Fabrizio Costa, Sauro Menchetti, and Paolo Frasconi
Mining structure-activity relations in biological neural networks using NeuronRank / Tayfun Gürel, Luc De Raedt, and Stefan Rotter
Adaptive contextual processing of structured data by recursive neural networks: a survey of computational properties / Barbara Hammer, Alessio Micheli, and Alessandro Sperduti
Markovian bias of neural-based architectures with feedback connections / Peter Tiňo, Barbara Hammer, and Mikael Bodén
Time series prediction with the self-organizing map: a review / Guilherme A. Barreto
A dual interaction perspective for robot cognition: grasping as a "Rosetta stone" / Helge Ritter, Robert Haschke, and Jochen J. Steil
SHRUTI: a neurally motivated architecture for rapid, scalable inference / Lokendra Shastri
The core method: connectionist model generation for first-order logic programs / Sebastian Bader [and others]
Learning models on predicate logical theories with neural networks based on topos theory / Helmar Gust, Kai-Uwe Kühnberger, and Peter Geibel
Advances in neural-symbolic learning systems: modal and temporal reasoning / Artur S. d'Avila Garcez
Connectionist representation of multi-valued logic programs / Ekaterina Komendantskaya, Máire Lane and Anthony Karel Seda
English