Making computers explain themselves
New training technique would reveal the basis for machine-learning systems’ decisions.
New training technique would reveal the basis for machine-learning systems’ decisions.
MegaMIMO system from the Computer Science and Artificial Intelligence Lab speeds data transfer by coordinating multiple routers at the same time.
New design should enable much more flexible traffic management, without sacrificing speed.
Analysis of ant colony behavior could yield better algorithms for network communication.
Batches of shoebox-sized satellites could improve estimates of Earth’s reflected energy.
Network can protect users’ anonymity if all but one of its servers are compromised.
New book by Senseable City Lab researchers presents vision of data-driven urban design.
Deep-learning vision system from the Computer Science and Artificial Intelligence Lab anticipates human interactions using videos of TV shows.
Video-trained system from MIT’s Computer Science and Artificial Intelligence Lab could help robots understand how objects interact with the world.
Bringing together engineers, data theorists, mathematicians, economists, biologists, and policy experts, IDSS is looking at financial risk through a multidisciplinary lens.
Researchers in IDSS are learning how ideas evolve over networks, quantifying the influence of individuals in networks, and making better predictions.
System from MIT’s Computer Science and Artificial Intelligence Lab enables single WiFi access point that can locate users within tens of centimeters.
"Polaris" system from MIT's Computer Science and Artificial Intelligence Lab accelerates website load-time by decreasing network trips.
Advance could enable mobile devices to implement “neural networks” modeled on the human brain.