Add BrightSurf on Google Email

Massachusetts Institute of Technology


Spotting objects amid clutter

Researchers at MIT develop a new algorithm that can accurately pick out an object, such as a small animal, in a dense cloud of dots within seconds. The technique prunes away outliers quickly, even for increasingly dense clouds, making it suitable for applications like driverless cars and robotic assistants.

Putting vision models to the test

Researchers at MIT have demonstrated that artificial neural networks can be used to drive specific brain neurons, showing a strong activation pattern. The study suggests that these models could be used to control brain states in animals and establish their usefulness, paving the way for further research.

Can science writing be automated?

A team of scientists at MIT developed a neural network that can read scientific papers and generate a plain-English summary. The system, called RUM, uses vectors rotating in multidimensional space to represent words and improve memory and recall capabilities.

SourceMassachusetts Institute of Technology·JournalTransactions of the Association for Computational Linguistics·DateApr 18, 2019