Explained: How to tell if artificial intelligence is working the way we want it to
“Interpretability methods” seek to shed light on how machine-learning models make predictions, but researchers say to proceed with caution.
Topic
Computer Science and Artificial Intelligence Laboratory (CSAIL)
Download RSS feed: News Articles / In the Media / Audio
A new twist on old-school animation
MIT researchers create KineCAM, an instant camera that yields images that appear to move.
Costis Daskalakis appointed inaugural Avanessians Professor in the MIT Schwarzman College of Computing
Professor of electrical engineering and computer science will receive additional support to advance his research and career.
3 Questions: Teaching computational maker skills through gaming
With FabO, PhD student Dishita Turakhia wants to empower students to learn digital fabrication by making video game objects and characters come alive.
Teaching AI to ask clinical questions
Researchers have made strides toward machine-learning models that can help doctors more efficiently find information in a patient’s health record.
Artificial intelligence model finds potential drug molecules a thousand times faster
A geometric deep-learning model is faster and more accurate than state-of-the-art computational models, reducing the chances and costs of drug trial failures.
A programming language for hardware accelerators
Researchers created Exo for writing high-performance code on hardware accelerators.
Remembering Octavian-Eugen Ganea, a gifted MIT postdoc AI researcher and beloved colleague
The brilliant scientist was known for both the depth of his intellect and his kindness.
Q&A: Neil Thompson on computing power and innovation
Rapid increases in the speed and power of microchips have fueled innovation in many industries, but the future trajectory of that incredible progress may be in jeopardy.
Taking the guesswork out of dental care with artificial intelligence
MIT alumni-founded Overjet analyzes and annotates dental X-rays to help dentists offer more comprehensive care.
Robots play with play dough
A new system lets robots manipulate soft, deformable material into various shapes from visual inputs, which could one day enable better home assistants.
Researchers release open-source photorealistic simulator for autonomous driving
MIT scientists unveil the first open-source simulation engine capable of constructing realistic environments for deployable training and testing of autonomous vehicles.
New model helps identify mutations that drive cancer
The system rapidly scans the genome of cancer cells, could help researchers find targets for new drugs.
Seeing the whole from some of the parts
A new technique in computer vision may enhance our three-dimensional understanding of two-dimensional images.
MIT-Northpond Program created to advance innovation in engineering and life sciences
The five-year collaboration aims to accelerate the translation of breakthrough engineering and biology for human health.