A team of researchers demonstrated that training machine learning models with synthetic images can outperform traditional training methods using real images.
MIT News From ACM TechNews | November 28, 2023
An algorithm developed by Massachusetts Institute of Technology researchers aims to identify potential failures in simulated autonomous systems prior to their real...MIT News From ACM TechNews | November 13, 2023
The Feature Fields for Robotic Manipulation method helps robots identify nearby objects by forming three-dimensional scenes from two-dimensional images and vision...MIT News From ACM TechNews | November 9, 2023
Neuroscientists studied the behavior of mice in a learn-reward situation, with the aim of teaching the mice to turn a wheel left or right to receive a reward.
MIT News From ACM TechNews | September 19, 2023
Massachusetts Institute of Technology and other researchers developed a technique that uses computer-generated data to help vision and language models better understand...MIT News From ACM TechNews | September 14, 2023
A team of researchers has developed a light-based machine learning system that could surpass the system behind ChatGPT in terms of power and efficiency, while also...MIT News From ACM TechNews | August 25, 2023
Massachusetts Institute of Technology researchers trained an artificial neural network to function like the brain's inferior temporal cortex to improve computer...MIT News From ACM TechNews | July 13, 2023
Scientists found computer vision models can be trained to produce more stable, predictable visual representations, similar to those humans learn through perceptual...MIT News From ACM TechNews | May 10, 2023