Called LOGAN, the deep neural network, i.e., a machine of sorts, can learn to transform the shapes of two different objects, for example, a chair and a table, in a natural way, without seeing any ...

To researchers’ surprise, deep learning vision algorithms often fail at classifying images because they mostly take cues from textures, not shapes. When you look at a photograph of a cat, chances are ...

Shape-selective neurons in inferotemporal cortex could carry information about either component parts or whole objects. A new paper now reports that whole-object shape selectivity is increased for ...

Join our daily and weekly newsletters for the latest updates and exclusive content on industry-leading AI coverage. Learn More State-of-the-art machine learning algorithms can extract two-dimensional ...

Researchers at the Institute of Science Tokyo have developed a neural-network-based 3D imaging technique that can precisely measure moving objects—a task long considered extremely challenging for ...

Instructional designers and educational technologists often talk about the potential for learning objects. Lego-like in their utility, learning objects are the small pedagogical chunks that can be ...