Scaling audio-visual learning without labels
A new multimodal technique blends major self-supervised learning methods to learn more similarly to humans.
A new multimodal technique blends major self-supervised learning methods to learn more similarly to humans.
Researchers develop an algorithm that decides when a “student” machine should follow its teacher, and when it should learn on its own.
Selecting the right method gives users a more accurate picture of how their model is behaving, so they are better equipped to correctly interpret its predictions.
A two-day conference at MIT reflected on the impact of the Institute for Data, Systems, and Society since its launch, as founding Director Munther Dahleh prepares to step down.
It’s more important than ever for artificial intelligence to estimate how accurately it is explaining data.
This machine-learning method could assist with robotic scene understanding, image editing, or online recommendation systems.
Senior Ananya Gurumurthy adds her musical talents to her math and computer science studies to advocate using data for social change.
With the artificial intelligence conversation now mainstream, the 2023 MIT-MGB AI Cures conference saw attendance double from previous years.
A new machine-learning model makes more accurate predictions about ocean currents, which could help with tracking plastic pollution and oil spills, and aid in search and rescue.
The CSAIL scientist describes natural language processing research through state-of-the-art machine-learning models and investigation of how language can enhance other types of artificial intelligence.