Charting a Safe Course for an Autonomous Robot Through a Highly Uncertain Environment
A new technique has been developed to safely guide an autonomous robot without knowledge of its environmental conditions or the size, shape, or location of…
Browsing tag
A new technique has been developed to safely guide an autonomous robot without knowledge of its environmental conditions or the size, shape, or location of…
MIT researchers create a mathematical framework to evaluate explanations of machine-learning models and quantify how well people understand them. Modern machine-learning models, such as neural…
“Privid” could help officials gather secure public health data or enable transportation departments to monitor the density and flow of pedestrians, without learning personal information…
A machine-learning model for image classification that’s trained using synthetic data can rival one trained on the real thing, a study shows. Huge amounts of…
A new technique could enable a robot to manipulate squishy objects like pizza dough or soft materials like clothing. Imagine a pizza maker working with…
CSAIL scientists came up with a learning pipeline for the four-legged robot that learns to run entirely by trial and error in simulation. It’s been…
Researchers find similarities between how some computer-vision systems process images and how humans see out of the corners of our eyes. Perhaps computer vision and…
Theories from cognitive science and psychology could help humans learn to collaborate with robots faster and more effectively, scientists find. Scientists who study human-robot interaction…
A new technique boosts models’ ability to reduce bias, even if the dataset used to train the model is unbalanced. If a machine-learning model is…
Researchers demonstrate a method that safeguards a computer program’s secret information while enabling faster computation. Multiple programs running on the same computer may not be…
Single-cell gene expression analyses of human cerebrovascular cells can help reveal new drug targets for Huntington’s disease. While neurons and glial cells are by far…
With a tensor language prototype, “speed and correctness do not have to compete … they can go together, hand-in-hand.” High-performance computing is needed for an…
An MIT team develops 3D-printed tags to classify and store data on physical objects. If you download music online, you can get accompanying information embedded…
A new method automatically describes, in natural language, what the individual components of a neural network do. Neural networks are sometimes called black boxes because,…
Time crystals. Microwaves. Diamonds. What do these three disparate things have in common? Quantum computing. Unlike traditional computers that use bits, quantum computers use qubits…
The new machine-learning system can generate a 3D scene from an image about 15,000 times faster than other methods. Humans are pretty good at looking…
Taking Some of the Guesswork Out of Drug Discovery A deep learning model rapidly predicts the 3D shapes of drug-like molecules, which could accelerate the…
The system could help physicians select the least risky treatments in urgent situations, such as treating sepsis. Sepsis claims the lives of nearly 270,000 people…