Concept-Oriented Deep Learning

Understand

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.