Researchers have successfully reproduced illusory motion in deep neural networks that were trained for perception. The DNNs were able to accurately reproduce the direction of illusory rotation humans observe while looking at a popular optical illusion.
Results from a new artificial intelligence study indicate number sense is spontaneously created by the visual system, without prior experience of counting.
Researchers have created a new audio-visual model that harnesses the power of deep neural networks that can isolate and enhance speech under natural conditions.
Artificial intelligence sheds new light on how the brain processes language. Researchers report the human brain may use next word prediction to drive language processing.
Researchers report artificial neural networks contain subnetworks that are considerably smaller, yet capable of being trained to make equally accurate predictions. Many subnetworks can learn to make accurate predictions much faster than the original networks.
A new study reveals neurons in the V4 area of the visual cortex do not necessarily need to have low visual resolution.
Researchers explain how deep neural networks are able to learn complex physics.
AI research has come full circle, helping neuroscientist better understand how the human brain works, researchers say.
Researchers have created a new deep learning algorithm that can accurately predict chronological age. The findings suggest the most accurate, non-invasive biomarker for aging prediction is the skin at the corner of the eye. Researchers say the findings could help offer solutions on how to look younger.