Neuro-Symbolic AI

As far back as the 1980s, researchers anticipated the role that deep neural networks could one day play in automatic image recognition and natural language processing. It took decades to amass the data and processing power required to catch up to that vision – but we’re finally here. Similarly, scientists have long anticipated the potential for symbolic AI systems to achieve human-style comprehension. And we’re just hitting the point where our neural networks are powerful enough to make it happen. We’re working on new AI methods that combine neural networks, which extract statistical structures from raw data files – context about image and sound files, for example – with symbolic representations of problems and logic. By fusing these two approaches, we’re building a new class of AI that will be far more powerful than the sum of its parts. These neuro-symbolic hybrid systems require less training data and track the steps required to make inferences and draw conclusions. They also have an easier time transferring knowledge across domains. We believe these systems will usher in a new era of AI where machines can learn more like the way humans do, by connecting words with images and mastering abstract concepts.

Top Work

CLEVRER: The first video dataset for neuro-symbolic reasoning

CLEVRER: The first video dataset for neuro-symbolic reasoning

Computers Already Learn From Us. But Can They Teach Themselves?

Computers Already Learn From Us. But Can They Teach Themselves?

04/08/2020 - The New York Times

All Work

This hybrid AI system can understand causality in controlled environments
This hybrid AI system can understand causality in controlled environments
TheNextWeb
Artificial intelligence is struggling to cope with how the world has changed
Artificial intelligence is struggling to cope with how the world has changed
ZDNet
Neuro-symbolic AI seen as evolution of artificial intelligence
Neuro-symbolic AI seen as evolution of artificial intelligence
TechTarget
How AI and supercomputing are going green
How AI and supercomputing are going green
ZDNet
CLEVRER: The first video dataset for neuro-symbolic reasoning
CLEVRER: The first video dataset for neuro-symbolic reasoning
Computers Already Learn From Us. But Can They Teach Themselves?
Computers Already Learn From Us. But Can They Teach Themselves?
The New York Times
Deep Symbolic Superoptimization Without Human Knowledge
Deep Symbolic Superoptimization Without Human Knowledge
Neuro-symbolic A.I. is the future of artificial intelligence. Here’s how it works
Neuro-symbolic A.I. is the future of artificial intelligence. Here’s how it works
Digital Trends
Top minds in machine learning predict where AI is going in 2020
Top minds in machine learning predict where AI is going in 2020
VentureBeat
Visual Concept-Metaconcept Learning
Visual Concept-Metaconcept Learning
 
What happens when you combine neural networks and rule-based AI?
What happens when you combine neural networks and rule-based AI?
Tech Talks
The AI Breakthrough Will Require Researchers Burying Their Hatchets
The AI Breakthrough Will Require Researchers Burying Their Hatchets
PC Mag
The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision
The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision
A Glimpse of A.I.’s Future? MIT-IBM Research Lab Sees Early Progress
A Glimpse of A.I.’s Future? MIT-IBM Research Lab Sees Early Progress
Xconomy
Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding
Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding