A Cognitive Modeling Approach to Learning of Ill-defined Categories
Explore this paper's citation graph
Summary
The implementation of an Adaptive Concept Learning system designed to learn ill-defined categories by simulating human learning behavior is described, which is a more realistic simulation of concept learning bel]avior observed in human beings.
- Type
- article
- Published
- 1996-01-01
- Cited by
- 1
- References
- 42
- OpenAlex
- https://openalex.org/W147687939
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:14841700
Keywords
Extant taxon, Cognitive science, Cognition, Computer science, Contrast (vision)
References
- Measuring Quality of Concept Descriptions
- From learning processes to cognitive processes
- Learning structural descriptions from examples
- A human learning approach for designing adaptive knowledge-based systems
- Inferential Theory of Learning: Developing Foundations for Multistrategy Learning
- Computer Systems That Learn
- Exemplar-Based Knowledge Acquisition
- Classification of empirically derived prototypes as a function of category experience
- Category Breadth and the Abstraction of Prototypical Information.
- Prototype abstraction and classification of new instances as a function of number of instances defining the prototype
- The relative contributions of common and distinctive information on the abstraction from ill-defined categories
- Retention of Abstract Ideas.
- Transcending inductive category formation in learning
- Retrieval and organizational strategies in conceptual memory: a computer model
- On the genesis of abstract ideas.
- Limitations of exemplar-based generalization and the abstraction of categorical information.
- A Comparative Review of Selected Methods for Learning from Examples
- Pattern recognition and categorization
- Categorization of Natural Objects
- Categories and concepts
Cited by
Related papers
- Concept learning via granular computing: A cognitive viewpoint
- Cognitive concept learning from incomplete information
- Learning as a Generative Process
- Cognitive ecology and social learning inspired machine learning: with particular reference to the evolving of resilient Airborne Networks (AN)
- LEARNING ABOUT COMPLEX SYSTEMS
- Understanding Cognitive Language Learning Strategies
- Neural-symbolic cognitive agents: architecture, theory and application
- A Cognitive Model for Effective E-Learning using Cognitive Architecture-ACT-R
- Learning without limits: from problem solving towards a Unified Theory of Learning