List, a CEA unit, says it has developed a new category of AI called multi-task deep learning. DeepManta, a flexible algorithm, can demonstrate visual object recognition for smart cities, such as identifying vehicles, their type and position and counting them. Different objects, such as miniature cars, move into a camera’s field of view, where the ...

This story continues at Deep Manta performs multi-task deep learning

Or just read more coverage at Electronics Weekly