Quantcast

Tiny Machine Learning Design Alleviates A Bottleneck In Memory Usage On Internet-Of-Things Devices

New technique applied to small computer chips enables efficient vision and detection algorithms without internet connectivity.

Scaling Audio-Visual Learning Without Labels

A new multimodal technique blends major self-supervised learning methods to learn more similarly to humans.

Latest News

Generating A Realistic 3D World

A new AI-powered, virtual platform uses real-world physics to simulate a rich and interactive audio-visual environment, enabling human and robotic learning, training, and experimental studies.

Deep-Learning Technique Predicts Clinical Treatment Outcomes

A new methodology simulates counterfactual, time-varying, and dynamic treatment strategies, allowing doctors to choose the best course of action.

Generating New Molecules With Graph Grammar

An efficient machine-learning method uses chemical knowledge to create a learnable grammar with production rules to build synthesizable monomers and polymers.

Hallucinating To Better Text Translation

A machine-learning method imagines what a sentence visually looks like, to situate and ground its semantics in the real world, improving translation, like humans can.

Neurodegenerative Disease Can Progress In Newly Identified Patterns

A machine-learning method finds patterns of health decline in ALS, informing future clinical trial designs and mechanism discovery. The technique also extends to Alzheimer’s and Parkinson’s.

Busy GPUS: Sampling And Pipelining Method Speeds Up Deep Learning On Large Graphs

New technique significantly reduces training and inference time on extensive datasets to keep pace with fast-moving data in finance, social networks, and fraud detection in cryptocurrency.

A One-Up On Motion Capture

A new neural network approach captures the characteristics of a physical system’s dynamic motion from video, regardless of rendering configuration or image differences.