Skip to content

Neuro-Symbolic Concept Learner

Massachusetts Institute of Technology (MIT)Tsinghua UniversityMIT-IBM Watson AI LabDeepMindVisual question answeringSemantic segmentation

The Neuro-Symbolic Concept Learner model is a visual question answering model from Massachusetts Institute of Technology (MIT),Tsinghua University,MIT-IBM Watson AI Lab,DeepMind.

About Neuro-Symbolic Concept Learner

We propose the Neuro-Symbolic Concept Learner (NS-CL), a model that learns visual concepts, words, and semantic parsing of sentences without explicit supervision on any of them; instead, our model learns by simply looking at images and reading paired

Details

Provider
Massachusetts Institute of Technology (MIT),Tsinghua University,MIT-IBM Watson AI Lab,DeepMind
Task
Visual question answering,Semantic segmentation
Released
2019-04-26
Open weights
No
View model source

Explore

FAQ