Computation and cognition: toward a foundation for cognitive science
Computation and cognition: toward a foundation for cognitive science
Artificial Intelligence
Knowledge acquisition as a constructive modeling activity
Knowledge acquisition as modeling
Task modeling with reusable problem-solving methods
Artificial Intelligence
Understanding, building and using ontologies
International Journal of Human-Computer Studies
Editorial: problem-solving methods
International Journal of Human-Computer Studies
A competence theory approach to problem solving method construction
International Journal of Human-Computer Studies
Knowledge engineering and management: the CommonKADS methodology
Knowledge engineering and management: the CommonKADS methodology
Reusable Components for Knowledge Modelling: Case Studies in Parametric Design Problem Solving
Reusable Components for Knowledge Modelling: Case Studies in Parametric Design Problem Solving
Common KADS Library for Expertise Modelling
Common KADS Library for Expertise Modelling
What Are Ontologies, and Why Do We Need Them?
IEEE Intelligent Systems
Diagnosis Systems in Medicine with Reusable Knowledge Components
IEEE Intelligent Systems
The Tower-of-Adapter Method for Developing and Reusing Problem-Solving Methods
EKAW '97 Proceedings of the 10th European Workshop on Knowledge Acquisition, Modeling and Management
UPML: A Framework for Knowledge System Reuse
IJCAI '99 Proceedings of the Sixteenth International Joint Conference on Artificial Intelligence
DIAGEN-WebDB: A Connectionist Approach to Medical Knowledge Representation and Inference
IWANN '01 Proceedings of the 6th International Work-Conference on Artificial and Natural Neural Networks: Connectionist Models of Neurons, Learning Processes and Artificial Intelligence-Part I
IEA/AIE '98 Proceedings of the 11th international conference on Industrial and engineering applications of artificial intelligence and expert systems: methodology and tools in knowledge-based systems
EUROMICRO '98 Proceedings of the 24th Conference on EUROMICRO - Volume 2
On how the computational paradigm can help us to model and interpret the neural function
Natural Computing: an international journal
A Recurrent Neural Network for Robotic Sensory-based Search
IWANN '03 Proceedings of the 7th International Work-Conference on Artificial and Natural Neural Networks: Part II: Artificial Neural Nets Problem Solving Methods
IWANN'03 Proceedings of the Artificial and natural neural networks 7th international conference on Computational methods in neural modeling - Volume 1
On the use of the computational paradigm in neurophysiology and cognitive science
IWINAC'05 Proceedings of the First international conference on Mechanisms, Symbols, and Models Underlying Cognition: interplay between natural and artificial computation - Volume Part I
On the physical formal and semantic frontiers between human knowing and machine knowing
EUROCAST'05 Proceedings of the 10th international conference on Computer Aided Systems Theory
Hi-index | 0.00 |
In this chapter we consider a number of methodological issues to which little importance is normally attributed in robotics but which we consider essential to the development of integrated methods of soft and hard computing and to the understanding of the artificial intelligence (AI) purpose and fundamentals.The basic conjecture in this chapter is that knowledge always remains at the knowledge level and in the external observer's domain. To the robot only pass the formal model underlying these models of knowledge. Consequently, there are neither essential differences between symbolic and connectionist techniques nor between soft and hard computing. They are different inferences and problem-solving-methods (PSMs) that belong to a library and that are selected to be used in a sequential or concurrent manner according to the suitability for decomposing the task under consideration, until we arrive to the level of inferential primitives solved in terms of data and relations specific of the application domain.The distinctive characteristics of hard and soft computing methods are related to the balance between knowledge and data available in advance, the granularity of the model or the necessity and capacity of learning in real time. Nevertheless, in all these cases the knowledge (the meaning of the entities and relations of the model) always is outside the robot, at the knowledge level, the "house" of models.In many publications, the robotic programs are described without including any distinction between levels and domains of description of a calculus. As a result, it is generally difficult to determine what the robot actually performs, which knowledge has been represented, and which is artificially injected during the human interpretation of the robots behavior.In order to make clear this methodological issues we consider the taxonomy of levels introduced by Marr [1] and Newell [2] (Knowledge, Symbols, and Hard-ware) put on the top of the two domains of description of a calculus (the domain proper of each level and that of the observer external to the computation of the level). Then, we describe the usual approach to modeling and reduction of models from the knowledge to the symbol level and finally we illustrate the analogies and differences between different models and reduction processes including the operational stage, either symbolic, connectionist, probabilistic or fuzzy. In all the cases our conviction is that most of the work must be made by modeling tasks and PSMs at the knowledge level, where it is crystal clear that soft and hard computing are complementary and ready to be integrated.