3,308 Hits in 3.4 sec

A Connectionist Model for Constructive Modal Reasoning

Artur S. d'Avila Garcez, Luís C. Lamb, Dov M. Gabbay
2005 Neural Information Processing Systems  
We present a new connectionist model for constructive, intuitionistic modal reasoning.  ...  This provides a massively parallel model for intuitionistic modal reasoning, and sets the scene for integrated reasoning, knowledge representation, and learning of intuitionistic theories in neural networks  ...  In this paper, we have presented a new model of computation that integrates neural networks and constructive, intuitionistic modal reasoning.  ... 
dblp:conf/nips/GarcezLG05 fatcat:6wq4zqpm2nebfhtheg27qblqju

Neural-Symbolic Computing: An Effective Methodology for Principled Integration of Machine Learning and Reasoning [article]

Artur d'Avila Garcez, Marco Gori, Luis C. Lamb, Luciano Serafini, Michael Spranger, Son N. Tran
2019 arXiv   pre-print
and explainable models for such systems.  ...  allowing for the construction of explainable AI systems.  ...  Notwithstanding, the need for richer cognitive models soon demanded the representation and learning of other forms of reasoning, such as temporal reasoning, reasoning about uncertainty, epistemic, constructive  ... 
arXiv:1905.06088v1 fatcat:gm4f3ncukrbevpd7nq5yr75ar4

Connectionist computations of intuitionistic reasoning

Artur S. d'Avila Garcez, Luís C. Lamb, Dov M. Gabbay
2006 Theoretical Computer Science  
The construction of computational models with provision for effective learning and added reasoning is a fundamental problem in computer science.  ...  This provides a massively parallel model for intuitionistic reasoning.  ...  As a result, each ensemble can be seen as a new massively parallel model for the computation of intuitionistic (modal) logic.  ... 
doi:10.1016/j.tcs.2005.11.043 fatcat:azyin6iqb5hh7mxuyl7abvmuuq

Mechanisms of Categorization in Infancy

Denis Mareschal, Robert French
2000 Infancy  
This article presents a connectionist model of correlation-based categorization by 10-month-old infants (Younger, 1985).  ...  The model provides a mechanistic account of category learning within a test session.  ...  This illustrates the function of a model as a tool for reasoning about untested contexts.  ... 
doi:10.1207/s15327078in0101_06 pmid:32680314 fatcat:xgp5z5sgpbcdjnu3zaxen554lq

Fewer Epistemological Challenges for Connectionism [chapter]

Artur S. d'Avila Garcez
2005 Lecture Notes in Computer Science  
Seventeen years ago, John McCarthy wrote the note Epistemological challenges for connectionism as a response to Paul Smolensky's paper On the proper treatment of connectionism.  ...  Lamb for useful discussions.  ...  The goal is to produce biologically plausible models with integrated reasoning and learning capability, in which neural networks provide the inspiration and the machinery necessary for cognitive computation  ... 
doi:10.1007/11494645_18 fatcat:hqscgo6shrgrdd4gn5lwimyyee

The human conceptual system

Lawrence W. Barsalou
2001 Proceedings of the international conference on Formal Ontology in Information Systems - FOIS '01  
For example, a photo of a wedding records the light present at each point in the scene without interpreting the types of entities and events present.  ...  Interpretation is productive, supporting the construction of complex conceptual representations from simpler ones.  ...  ·where connectionist models are weakest (like exemplar models) is on symbolic operations (Fodor and Pylyshyn, 1988) .  ... 
doi:10.1145/505168.505186 dblp:conf/fois/Barsalou01 fatcat:5kovwfutfva3zkldl2q7zcgg7i

Dimensions of Neural-symbolic Integration - A Structured Survey [article]

Sebastian Bader, Pascal Hitzler
2005 arXiv   pre-print
Recent work has covered a great variety of logics used in artificial intelligence and provides a multitude of techniques for dealing with them within the context of artificial neural networks.  ...  In particular the understanding of ways to deal with symbolic knowledge within connectionist systems (also called artificial neural networks) has reached a critical mass which enables the community to  ...  Reflexive Connectionist Reasoning A wide variety of tasks can be solved by humans very fast and efficiently. This type of reasoning is sometimes referred to as reflexive reasoning.  ... 
arXiv:cs/0511042v1 fatcat:wh4bv3oo35akncg3ds6djkws3m

Page 5538 of Mathematical Reviews Vol. , Issue 95i [page]

1995 Mathematical Reviews  
A connectionist model for minimization of the objective functions based on gradient descent in the space of inputs of a multilayer feedforward network is proposed.  ...  Masalagiu (R-IASI-SM;; Iasi) 95i:68025 68N17 03B60 03B70 68T27 Vingralek, Radek (1-K Y-C; Lexington, KY) Connectionist approach to finding stable models and other structures in nonmonotonic reasoning.  ... 

Applications of scott's notion of consequence to the study of general binary intensional connectives and entailment

Dov M. Gabbay
1973 Journal of Philosophical Logic  
Reidel, 1976. 321 pp, The main research thrust of this monograph is to present comprehensive methods for proving decidability and undecidability for modal and temporal systems.  ...  Counter examples are constructed to show the limitations of various methods. The book also lays the mathematical and conceptual foundations for non-classical logics.  ...  A Connectionist Model for Constructive Modal Reasoning ( with A. d'Avila Garcez and Luis C.). 2005.  ... 
doi:10.1007/bf00129607 fatcat:e6lokulrwrfcvl525fgj6dcr3m

Symbols and Subsymbols for Representing Knowledge: A Catalogue Raisonné

Marcello Frixione, Giuseppe Spinelli, Salvatore Gaglio
1989 International Joint Conference on Artificial Intelligence  
otherwise modelled.  ...  More recently the development of the connectionist paradigm has questioned the symbolic approach to the study of the mind bringing about a more articulated view of the problem.  ...  Acknowledgements We thank Diego Marconi, Luisa Montecucco and Carlo Penco for their helpful and insightful comments, and Edward Farrants for preparing the English version.  ... 
dblp:conf/ijcai/FrixioneSG89 fatcat:jumnnsg35vb6ffvfikibahlgam

Parsing Complex Sentences with Structured Connectionist Networks

Ajay N. Jain
1991 Neural Computation  
This offers a potential solution to the difficult prob- lem of constructing grammars for spoken language.  ...  Earlier work produced a connectionist architecture that learned to parse a small set of sentences, including some with passive constructions (Jain 1989).  ... 
doi:10.1162/neco.1991.3.1.110 fatcat:e7jq4bfrufd7vkfvqmsqxsq7xi

Page 935 of Linguistics and Language Behavior Abstracts: LLBA Vol. 29, Issue 3 [page]

1995 Linguistics and Language Behavior Abstracts: LLBA  
It is precisely this claim that F&P level at recent ad- vances in a more connectionist model of cognition.  ...  Results indicated that for each emotion there is a modal category, which frequently was identical, & some secondary categories that varied con- siderably with culture.  ... 

Logic programs and connectionist networks

Pascal Hitzler, Steffen Hölldobler, Anthony Karel Seda
2004 Journal of Applied Logic  
In this paper, we show that certain semantic operators for propositional logic programs can be computed by feedforward connectionist networks, and that the same semantic operators for first-order normal  ...  Turning the networks into recurrent ones allows one also to approximate the models associated with the semantic operators.  ...  Representation and Reasoning Group at TU Dresden, (ii) Deutscher Akademischer Austausch Dienst (DAAD), and (iii) the Boole Centre for Research in Informatics at University College Cork.  ... 
doi:10.1016/j.jal.2004.03.002 fatcat:3uupzwgp2ba7hf6mv7jvsvllye

Why Children Don't Have to Solve the Frame Problems: Cognitive Representations Are Not Encodings

Mark H Bickhard
2001 Developmental Review  
Conversely, the interactive alternative model of representation that I offer has its own powerful consequences for development -the issues at stake are not trivial. 1 Chomsky showed that the age of the  ...  I argue that this assumption is false, and offer an alternative model of representation based on the pragmatics of action.  ...  This is a straightforward application of mental models to modal reasoning.  ... 
doi:10.1006/drev.2000.0521 fatcat:ndiw24exfjbo7hpzsbvoqaat6i

Connectionist modal logic: Representing modalities in neural networks

Artur S. d'Avila Garcez, Luís C. Lamb, Dov M. Gabbay
2007 Theoretical Computer Science  
We show that the translation is sound, i.e. the network ensemble computes a fixed-point meaning of the original modal program, acting as a distributed computational model for modal logic.  ...  Finally, we validate CML as a computational model for integrated knowledge representation and learning by applying it to a well-known testbed for distributed knowledge representation.  ...  Acknowledgements We are grateful to Stefan Holldobler and the anonymous referees for their useful comments. Artur Garcez is partly funded by The Royal Society, UK.  ... 
doi:10.1016/j.tcs.2006.10.023 fatcat:xjm4htxjubczdllcdyj5l76bxa
« Previous Showing results 1 — 15 out of 3,308 results