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.
A technique to improve both fairness and accuracy in artificial intelligence
Methods that make a machine-learning model’s predictions more accurate overall can reduce accuracy for underrepresented subgroups. A new approach can help.
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.
Smart textiles sense how their users are moving
Researchers develop a comfortable, form-fitting fabric that recognizes its wearer’s activities, like walking, running, and jumping.
Startup lets doctors classify skin conditions with the snap of a picture
Piction Health, founded by Susan Conover SM ’15, uses machine learning to help physicians identify and manage skin disease.
Building explainability into the components of machine-learning models
Researchers develop tools to help data scientists make the features used in machine-learning models more understandable for end users.
Exploring emerging topics in artificial intelligence policy
The second AI Policy Forum Symposium convened global stakeholders across sectors to discuss critical policy questions in artificial intelligence.
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.
Seeing the whole from some of the parts
A new technique in computer vision may enhance our three-dimensional understanding of two-dimensional images.
Artificial neural networks model face processing in autism
A new computational model could explain differences in recognizing facial emotions.
Engineers build LEGO-like artificial intelligence chip
The new design is stackable and reconfigurable, for swapping out and building on existing sensors and neural network processors.
Student-powered machine learning
Recent MEng graduates reflect on their application-focused research as affiliates of the MIT-IBM Watson AI Lab.