Machine-learning system tackles speech and object recognition, all at once
Model learns to pick out objects within an image, using spoken descriptions.
Download RSS feed: News Articles / In the Media / Audio
Model learns to pick out objects within an image, using spoken descriptions.
Machine learning system efficiently recognizes activities by observing how objects change in only a few key frames.
Three MIT postdocs earn competitive Howard Hughes Medical Institute fellowships that support diversity in the sciences.
MIT-developed tool improves automated image vectorization, saving digital artists time and effort.
Breakthrough CSAIL system suggests robots could one day be able to see well enough to be useful in people’s homes and offices.
Neural network learns speech patterns that predict depression in clinical interviews.
By training on patients grouped by health status, neural network can better estimate if patients will die in the hospital.
CSAIL wireless system suggests future where doctors could implant sensors to track tumors or even dispense drugs.
Novel combination of two encryption techniques protects private data, while keeping neural networks running quickly.
Users can quickly visualize designs that optimize multiple parameters at once.
CSAIL system encourages government transparency using cryptography on a public log of wiretap requests.
Iconic composer A. R. Rahman visits MIT campus to learn more about new technologies.
Professor of electrical engineering and computer science is honored for his contributions to theoretical computer science.
Silicon-based system offers smaller, cheaper alternative to other “broadband” filters; could improve a variety of photonic devices.
FinTech@CSAIL industry collaboration will work to improve business models, access to data, and security in the finance sector.