Neural-Symbolic Learning and Reasoning: Contributions and Challenges

The goal of neural-symbolic computation is to integrate robust connectionist learning and sound symbolic reasoning. With the recent advances in connectionist learning, in particular deep neural networks, forms of representation learning have emerged. However, such representations have not become useful for reasoning. Results from neural-symbolic computation have shown to offer powerful alternatives for knowledge representation, learning and reasoning in neural computation. This paper recalls the main contributions and discusses key challenges for neural-symbolic integration which have been identified at a recent Dagstuhl seminar.

[1]  Vladimir Lifschitz,et al.  Answer set programming and plan generation , 2002, Artif. Intell..

[2]  Artur S. d'Avila Garcez,et al.  Neural Relational Learning Through Semi-Propositionalization of Bottom Clauses , 2015, AAAI Spring Symposia.

[3]  Krysia Broda,et al.  First-order logic learning in Artificial Neural Networks , 2010, The 2010 International Joint Conference on Neural Networks (IJCNN).

[4]  Dov M. Gabbay,et al.  Neural-Symbolic Cognitive Reasoning , 2008, Cognitive Technologies.

[5]  Andreas Witzel,et al.  A Fully Connectionist Model Generator for Covered First-Order Logic Programs , 2007, IJCAI.

[6]  Rutvik H. Desai,et al.  The neurobiology of semantic memory , 2011, Trends in Cognitive Sciences.

[7]  Sebastian Rudolph,et al.  Complexities of Horn Description Logics , 2013, TOCL.

[8]  Luc De Raedt,et al.  Guest editorial to the special issue on inductive logic programming, mining and learning in graphs and statistical relational learning , 2010, Machine Learning.

[9]  Sebastian Rudolph,et al.  On the Complexity of Horn Description Logics , 2006, OWLED.

[10]  Daniel L. Silver,et al.  On Common Ground : Neural-Symbolic Integration and Lifelong Machine Learning , 2013 .

[11]  Jerome Feldman,et al.  The neural binding problem(s) , 2013, Cognitive Neurodynamics.

[12]  Daniel L. Silver.  The Consolidation of Task Knowledge for Lifelong Machine Learning , 2013, AAAI Spring Symposium: Lifelong Machine Learning.

[13]  Jerome A. Feldman,et al.  From Molecule to Metaphor - A Neural Theory of Language , 2006 .

[14]  Guido Boella,et al.  Learning and reasoning about norms using neural-symbolic systems , 2012, AAMAS.

[15]  Bernhard Ganter,et al.  Formal Concept Analysis: Mathematical Foundations , 1998 .

[16]  D. Gentner,et al.  The analogical mind : perspectives from cognitive science , 2001 .

[17]  P. Smolensky.  On the proper treatment of connectionism , 1988, Behavioral and Brain Sciences.

[18]  Pascal Hitzler,et al.  Ontology learning as a use-case for neural-symbolic integration , 2005, IJCAI 2005.

[19]  S. Tran,et al.  Knowledge Extraction from Deep Belief Networks for Images , 2013 .

[20]  Leslie G. Valiant,et al.  Knowledge Infusion: In Pursuit of Robustness in Artificial Intelligence , 2008, FSTTCS.

[21]  Dan Roth,et al.  Learning to Reason with a Restricted View , 1995, COLT '95.

[22]  Andrew McCallum,et al.  Introduction to Statistical Relational Learning , 2007 .

[23]  Krysia Broda,et al.  Symbolic knowledge extraction from trained neural networks: A sound approach , 2001, Artif. Intell..

[24]  Jude W. Shavlik,et al.  in Advances in Neural Information Processing , 1996 .

[25]  Artur S. d'Avila Garcez,et al.  Learning and Representing Temporal Knowledge in Recurrent Networks , 2011, IEEE Transactions on Neural Networks.

[26]  Luc De Raedt,et al.  Probabilistic Inductive Logic Programming - Theory and Applications , 2008, Probabilistic Inductive Logic Programming.

[27]  Moshe Y. Vardi.  Why is Modal Logic So Robustly Decidable? , 1996, Descriptive Complexity and Finite Models.

[28]  Gilles Richard,et al.  Computational Approaches to Analogical Reasoning: Current Trends , 2014, Computational Approaches to Analogical Reasoning.

[29]  Artur S. d'Avila Garcez,et al.  Fast relational learning using bottom clause propositionalization with artificial neural networks , 2013, Machine Learning.

[30]  Pascal Hitzler,et al.  OWL and Rules , 2011, Reasoning Web.

[31]  Daniel L. Silver,et al.  Consolidation Using Context-Sensitive Multiple Task Learning , 2011, Canadian Conference on AI.

[32]  Artur S. d'Avila Garcez,et al.  A Neural-Symbolic Cognitive Agent for Online Learning and Reasoning , 2011, IJCAI.

[33]  Pascal Hitzler,et al.  A better uncle for OWL: nominal schemas for integrating rules and ontologies , 2011, WWW.

[34]  Dan Roth,et al.  Learning to reason , 1994, JACM.

[35]  Artur S. d'Avila Garcez,et al.  A Connectionist Computational Model for Epistemic and Temporal Reasoning , 2006, Neural Computation.

[36]  Gadi Pinkas,et al.  A Dynamic Binding Mechanism for Retrieving and Unifying Complex Predicate-Logic Knowledge , 2012, ICANN.

[37]  Kai-Uwe Kühnberger,et al.  Heuristic-Driven Theory Projection: An Overview , 2014, Computational Approaches to Analogical Reasoning.

[38]  Brian Falkenhainer,et al.  The Structure-Mapping Engine: Algorithm and Examples , 1989, Artif. Intell..

[39]  W. Pitts,et al.  A Logical Calculus of the Ideas Immanent in Nervous Activity (1943) , 2021, Ideas That Created the Future.

[40]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

[41]  John McCarthy,et al.  Epistemological challenges for connectionism , 1988, Behavioral and Brain Sciences.

[42]  Ron Sun,et al.  Integrating rules and connectionism for robust commonsense reasoning , 1994, Sixth-generation computer technology series.

[43]  Pascal Hitzler,et al.  Connectionist model generation: A first-order approach , 2008, Neurocomputing.

[44]  Leslie G. Valiant,et al.  A neuroidal architecture for cognitive computation , 1998, ICALP.

[45]  Leslie G. Valiant,et al.  Knowledge Infusion , 2006, AAAI.

[46]  Jude W. Shavlik,et al.  Understanding Time-Series Networks: A Case Study in Rule Extraction , 1997, Int. J. Neural Syst..

[47]  Qiang Yang,et al.  Heterogeneous Transfer Learning for Image Clustering via the SocialWeb , 2009, ACL.

[48]  Brendan Juba,et al.  Implicit Learning of Common Sense for Reasoning , 2013, IJCAI.

[49]  Kai-Uwe Kühnberger,et al.  Learning Models of Predicate Logical Theories with Neural Networks Based on Topos Theory , 2007, Perspectives of Neural-Symbolic Integration.

[50]  Jens Lehmann,et al.  Extracting reduced logic programs from artificial neural networks , 2010, Applied Intelligence.

[51]  Geoffrey E. Hinton.  Preface to the Special Issue on Connectionist Symbol Processing , 1990 .

[52]  Bernhard Beckert,et al.  Dynamic Logic , 2007, The KeY Approach.

[53]  Krysia Broda,et al.  Neural-symbolic learning systems - foundations and applications , 2012, Perspectives in neural computing.

[54]  Dov M. Gabbay,et al.  Connectionist modal logic: Representing modalities in neural networks , 2007, Theor. Comput. Sci..

[55]  Uta Priss,et al.  An application of formal concept analysis to semantic neural decoding , 2009, Annals of Mathematics and Artificial Intelligence.