Algorithms designed to ensure multiple users share a network fairly can’t prevent some users from hogging all the bandwidth.
By continuously monitoring a patient’s gait speed, the system can assess the condition’s severity between visits to the doctor’s office.
A new technique enables AI models to continually learn from new data on intelligent edge devices like smartphones and sensors, reducing energy costs and privacy risks.
A new method uses optics to accelerate machine-learning computations on smart speakers and other low-power connected devices.
Researchers develop a technique for precisely arranging nanoscale particles on a surface, such as a silicon chip, that doesn’t damage the material.
This machine-learning system can simulate how a listener would hear a sound from any point in a room.
A new approach sheds light on the behavior of turbulent structures that can affect the energy generated during fusion reactions, with implications for reactor design.
New system can teach a group of cooperative or competitive AI agents to find an optimal long-term solution.
New research reveals a scalable technique that uses synthetic data to improve the accuracy of AI models that recognize images.
Researchers have developed a programmable optical device for high-speed beam steering.
New technique could diminish errors that hamper the performance of super-fast analog optical neural networks.
This computational tool can generate an optimal design for a complex fluidic device such as a combustion engine or a hydraulic pump.
Study shows that if autonomous vehicles are widely adopted, hardware efficiency will need to advance rapidly to keep computing-related emissions in check.
A new measure can help scientists decide which estimation method to use when modeling a particular data problem.
A new study shows how large language models like GPT-3 can learn a new task from just a few examples, without the need for any new training data.
The method enables a model to determine its confidence in a prediction, while using no additional data and far fewer computing resources than other methods.
The device could help workers locate objects for fulfilling e-commerce orders or identify parts for assembling products.
Researchers used machine learning to build faster and more efficient hash functions, which are a key component of databases.
New repair techniques enable microscale robots to recover flight performance after suffering severe damage to the artificial muscles that power their wings.
A new system enables makers to incorporate sensors into gears and other rotational mechanisms with just one pass in a 3D printer.