Concept-Oriented Deep Learning: Generative Concept Representations
Generative concept representations have three major advantages over discriminative ones: they can represent uncertainty, they support integration of learning and reasoning, and they are good for unsupervised and semi-supervised learning. We discuss probabilistic and generative deep learning, which generative concept representations are based on, and the use of variational autoencoders and generative adversarial networks for learning generative concept representations, particularly for concepts whose data are sequences, structured data or graphs.
Code (0)
등록된 구현이 없습니다.
Tasks
Deep LearningSimilar Papers 제목 키워드 기반
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 representatio…
Continual LearningDeep LearningRepresentation LearningAlgorithmic Causal Deconvolution of Intertwined Programs and Networks by Generative Mechanism
Complex data usually results from the interaction of objects produced by different generating mechanisms. Here we introduce a universal, unsupervised and parameter-free model-oriented approach, based upon the seminal con…
Few-Shot Task Learning through Inverse Generative Modeling
Learning the intents of an agent, defined by its goals or motion style, is often extremely challenging from just a few examples. We refer to this problem as task concept learning and present our approach, Few-Shot Task L…
Autonomous DrivingNovel ConceptsObject RearrangementDual Embodied-Symbolic Concept Representations for Deep Learning
Motivated by recent findings from cognitive neural science, we advocate the use of a dual-level model for concept representations: the embodied level consists of concept-oriented feature representations, and the symbolic…
class-incremental learningClass Incremental LearningDeep LearningFew-Shot Class-Incremental Learning+8Latent Variable Modeling for Generative Concept Representations and Deep Generative Models
Latent representations are the essence of deep generative models and determine their usefulness and power. For latent representations to be useful as generative concept representations, their latent space must support la…
Attribute