Caption:

Chris Rackauckas’ research is at the intersection of domain models with artificial intelligence techniques like machine learning.

Researchers create a mathematical framework to evaluate explanations of machine-learning models and quantify how well people understand them.

MIT researchers developed a machine learning technique that learns to represent data in a way that captures concepts which are shared between visual and audio modalities. Their model can identify where certain action is taking place in a video and label it.

A new neural network approach captures the characteristics of a physical system’s dynamic motion from video, regardless of rendering configuration or image differences.

MIT researchers can now estimate how much information data are likely to contain, in a more accurate and scalable way than previous methods.

A new machine-learning system may someday help driverless cars predict the next moves of nearby drivers, cyclists, and pedestrians in real-time.

A new technique compares the reasoning of a machine-learning model to that of a human, so the user can see patterns in the model’s behavior.

An efficient machine-learning method uses chemical knowledge to create a learnable grammar with production rules to build synthesizable monomers and polymers.