Topics

Researchers have found a way to visualize how deep neural networks organize information, which helps spotting errors.

Researchers use an AI model to build a highly detailed map of the mouse brain, revealing new areas that could improve understanding of brain functions, behaviors, and diseases.

Researchers create an AI that reads studies, analyzes data, and predicts molecule behavior to speed up science.

Exascale supercomputers to transform deep neural networks and online data analysis

Researchers develop a machine-learning approach to bend sub-terahertz transmissions, dodging blocks in dynamic spaces for faster wireless data in virtual reality and autonomous vehicles.

Scientists use sound waves to create a new photonic activation function, advancing energy-efficient AI with optical neural networks.

Researchers discover the maximum precision possible in optical imaging and use AI to nearly reach this limit for better medical imaging.

Study reveals large language models fall short in capturing sensory and motor experiences of human concepts compared to human understanding.

Researchers develop a new type of neural network that learns continually with much lower power consumption than today's large AI models.

Researchers at Chalmers University of Technology teach neural networks the laws of physics and electromagnetism to design light-controlling materials much faster.