Concept-Oriented Deep Learning
Concepts are the foundation of human deep learning, understanding, and knowledge integration and transfer. We propose concept-oriented deep learning (CODL) which extends (machine) deep learning with concept representations and conceptual understanding capability. CODL addresses some of the major limitations of deep learning: interpretability, transferability, contextual adaptation, and requirement for lots of labeled training data. We discuss the major aspects of CODL including concept graph, concept representations, concept exemplars, and concept representation learning systems supporting incremental and continual learning.
Code (0)
등록된 구현이 없습니다.
Tasks
Continual LearningDeep LearningRepresentation LearningSimilar Papers 제목 키워드 기반
Concept-Oriented Deep Learning with Large Language Models
Large Language Models (LLMs) have been successfully used in many natural-language tasks and applications including text generation and AI chatbots. They also are a promising new technology for concept-oriented deep learn…
Deep LearningText GenerationLearning Machines: In Search of a Concept Oriented Language
What is the next step after the data/digital revolution? What do we need the most to reach this aim? How machines can memorize, learn or discover? What should they be able to do to be qualified as "intelligent"? These qu…
Decision MakingReducing fuzzy relation equations via concept lattices
This paper has taken into advantage the relationship between Fuzzy Relation Equations (FRE) and Concept Lattices in order to introduce a procedure to reduce a FRE, without losing information. Specifically, attribute redu…
AttributeRelationIntention Reasoning Network for Multi-Domain End-to-end Task-Oriented Dialogue
Recent years has witnessed the remarkable success in end-to-end task-oriented dialog system, especially when incorporating external knowledge information. However, the quality of most existing models’ generated response …