1,136 Hits in 5.4 sec

Hybrid Connectionist-Symbolic Modules: A Report from the IJCAI-95 Workshop on Connectionist-Symbolic Integration

Ron Sun
1996 The AI Magazine  
The general consensus was that hybrid connectionist-symbolic models constitute a promising avenue to the development of more robust, more powerful, and more versatile architectures for both cognitive modeling  ...  The focus of the workshop was on learning and architectures that feature hybrid representations and support hybrid learning.  ...  Acknowledgment I want to thank Frederic Alexandre, Michael Dyer, John Barnden, Larry Bookman, Noel Sharkey, Jim Hendler, and other members of the committee for their roles in organizing this workshop.  ... 
doi:10.1609/aimag.v17i2.1225 dblp:journals/aim/Sun96 fatcat:gfqhf6cfmrdxddsazbaqkwf3qq

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

Sebastian Bader, Pascal Hitzler
2005 arXiv   pre-print
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  ...  We present a comprehensive survey of the field of neural-symbolic integration, including a new classification of system according to their architectures and abilities.  ...  Local versus Distributed Representation of Knowledge For integrated neural-symbolic systems, the question is crucial how symbolic knowledge is represented within the connectionist system.  ... 
arXiv:cs/0511042v1 fatcat:wh4bv3oo35akncg3ds6djkws3m

The Present and the Future of Hybrid Neural Symbolic Systems: Some Reflections from the NIPS Workshop

Stefan Wermter, Ron Sun
2001 The AI Magazine  
In Feldman and Bailey's talk, it was proposed that there are the following distinct levels: cognitive linguistic, computational, structured connectionist, computational biological, and biological.  ...  In terms of the relation between symbolic and neural knowledge during learning, we have the following possibilities: (1) purely neural learning of symbolic knowledge (for example, The Present and the  ...  Sun's research interest centers on the studies of intelligence and cognition, especially in the areas of commonsense reasoning, human and machine learning, and hybrid connectionist models.  ... 
doi:10.1609/aimag.v22i1.1551 dblp:journals/aim/WermterS01 fatcat:hhoutpiucbfebmwwxxwukctkgu

Representational Issues in the Debate on the Standard Model of the Mind [article]

Antonio Chella, Marcello Frixione, Antonio Lieto
2018 arXiv   pre-print
Finally, we briefly analyze the alternative representational assumptions employed in the three CAs constituting the current baseline for the Standard Model (i.e. SOAR, ACT-R and Sigma).  ...  In doing so we outline some of the main problems affecting the current CAs and suggest that the Conceptual Spaces, a representational framework developed by Gardenfors, is worth-considering to address  ...  Some of them adopt a symbolic approach, some are based on a purely connectionist model, while others adopt a hybrid approach combining connectionist and symbolic representational levels.  ... 
arXiv:1804.08299v1 fatcat:pjiaibsa2ff3zkdlogo53jjg2e

A component-based architecture for flexible integration of robotic systems

Min Yang Jung, A Deguet, P Kazanzides
2010 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems  
The formal underpinnings and perceptual processes are described in the context of a biohazard detection task.  ...  The architecture is based on the conceptual spaces representation that Gärdenfors suggested as an alternative to more traditional AI approaches.  ...  However, classical knowledge representations (e.g., symbolic representations and connectionist methods) have several deficits such as the frame and symbol grounding problems, and can exhibit difficulty  ... 
doi:10.1109/iros.2010.5652394 dblp:conf/iros/JungDK10 fatcat:roe56akfqfdmldhnra7zsorog4

Knowledge Processing

B. de Faria Leão
1996 IMIA Yearbook of Medical Informatics  
Hybrid connectionist expert systems were, therefore, proposed, integrating symbolic and connectionist paradigms, both supporting each other.  ...  This paradigm is based on a distributed object environment with services and brokers to handle integration with different and heterogeneous applications.  ... 
doi:10.1055/s-0038-1638062 fatcat:c2lmhk2i2zabdgzcbm7rmuc42i

The knowledge level in cognitive architectures: Current limitations and possible developments

Antonio Lieto, Christian Lebiere, Alessandro Oltramari
2018 Cognitive Systems Research  
In this paper we identify and characterize an analysis of two problematic aspects affecting the representational level of cognitive architectures (CAs): the size and the typology of the encoded knowledge  ...  representation and processing mechanisms with those executed by humans in their everyday activities.  ...  The integration of ACT-R18 mechanisms to a symbolic knowledge base.  ... 
doi:10.1016/j.cogsys.2017.05.001 fatcat:ze4iluck3fabtiz7zwy4qbzuha

Knowledge graph using resource description framework and connectionist theory

Ravi Lourdusamy, Xavierlal J Mattam
2020 Journal of Physics, Conference Series  
The weighted RDF in Graph Neural Network will represent the knowledge graph using RDF and connectionist theory.  ...  Interest in Knowledge Graph has peeked these years.  ...  Motivation The connectionist or sub-symbolic approaches employing artificial neural network fundamentally differs from the symbolic approaches that use logic and reasoning in a knowledge graph.  ... 
doi:10.1088/1742-6596/1427/1/012001 fatcat:uqnd3tliczdhtarlu256inzjtu

Reasoning with Deep Learning: an Open Challenge

Marco Lippi
2016 International Conference of the Italian Association for Artificial Intelligence  
In particular, providing an effective integration of learning and reasoning mechanisms is a long-standing research problem at the intersection of many different areas, such as machine learning, cognitive  ...  neuroscience, psychology, linguistic, and logic.  ...  Pioneering approaches Throughout the years, there have been many attempts to combine learning and reasoning processes by integrating connectionist and symbolic paradigms.  ... 
dblp:conf/aiia/Lippi16 fatcat:bygkeanwrnhnrp645eqtd5vx3m

User-centered visual analysis using a hybrid reasoning architecture for intensive care units

Bernard Kamsu-Foguem, Germaine Tchuenté-Foguem, Laurent Allart, Youcef Zennir, Christian Vilhelm, Hossein Mehdaoui, Djamel Zitouni, Hervé Hubert, Mohamed Lemdani, Pierre Ravaux
2012 Decision Support Systems  
The action sequences performed on the graphical user interface by the user are consolidated in a dynamic knowledge base with specific hybrid reasoning that integrates symbolic and connectionist approaches  ...  We present a knowledge-and machine learning-based approach to support the knowledge discovery process with appropriate analytical and visual methods.  ...  The computation module is a neuro-symbolic engine for medical knowledge representation and reasoning.  ... 
doi:10.1016/j.dss.2012.06.009 fatcat:lm3j7jy3sbathfwbl4dmlqzwui

Editorial Commentary

1988 Behavioral and Brain Sciences  
The level of analysis is intermediate between those of symbolic cognitive models and neural models.  ...  Higher-level analyses of these connectionist models reveal subtle relations to symbolic models.  ...  To say that knowledge in a connectionist computer program is manifest within a system of weights and differential equations is not only a retreat from symbolic meaning representation, it's a retreat from  ... 
doi:10.1017/s0140525x00052791 fatcat:7o7kyja25jfztfovklj74nqt3y

Representational Limits in Cognitive Architectures

Antonio Lieto
2016 EUCognition  
As a possible way out to face, jointly, these problems, this contribution discusses the possibility of integrating external, but architecturally compliant, cognitive systems into the knowledge representation  ...  In particular, it addresses the problems regarding both the limited size and the homogeneous typology of the encoded (and processed) conceptual knowledge.  ...  The arguments presented in this paper have been discussed in different occasions with Christian Lebiere, Alessandro Oltramari, Antonio Chella, Marcello Frixione, Peter Gärdenfors, Valentina Rho and Daniele  ... 
dblp:conf/eucognition/Lieto16 fatcat:tsl22lrhzrdhbmxlkmddtudt4i

Combining Data-Driven and Knowledge-Based AI Paradigms for Engineering AI-Based Safety-Critical Systems

Juliette Mattioli, Gabriel Pedroza, Souhaiel Khalfaoui, Bertrand Leroy
2022 AAAI Conference on Artificial Intelligence  
The proposed paradigm recognizes existing AI approaches, namely connectionist, symbolic, and hybrid, and proffers to leverage their essential traits captured as knowledge.  ...  A conceptual meta-body is thus obtained respectively containing categories for Data-, Knowledge-and Hybrid-driven.  ...  More recently (Sun 2015), hybrid approaches integrating symbolic-based and connectionist paradigms have been proposed.  ... 
dblp:conf/aaai/MattioliPKL22 fatcat:b6yflydkjravvjg6cqe3ygwnni

Framework of fully integrated hybrid systems

A. Santos, J. J. Romero, A. Carballal, A. Pazos
2011 Neural computing & applications (Print)  
Tightly coupled systems include common representation structures which allow two-directional information exchanges between connectionist and symbolic modules enabling parallel processing.  ...  On the other hand, a master-slave kind of configuration between the connectionist and the symbolic modules does not facilitate a thorough integration.  ... 
doi:10.1007/s00521-011-0672-9 fatcat:qaaujnjc3jfbvfbwqinrgeaide

Indispensability of Computational Modeling in Cognitive Science

Igor Farkaš
2012 Journal of Cognitive Science  
-symbolic, connectionist, dynamic and probabilistic.  ...  The concept of computation remains a frequently discussed topic in cognitive science, but there is no consensus about its meaning and the role in this field.  ...  Connectionist, dynamical and probabilistic approaches may become in the future more integrated within the computational cognitive science (McClelland, 2009 ).  ... 
doi:10.17791/jcs.2012.13.4.401 fatcat:fxr4sbkcbbhijmfecyo2tgvps4
« Previous Showing results 1 — 15 out of 1,136 results