AI News, Illusory motion reproduced by deep neural networks trained for prediction

Illusory motion reproduced by deep neural networks trained for prediction

A research team led by associate professor Eiji Watanabe of the National Institute for Basic Biology successfully reproduced illusory motion by DNNs trained for prediction.

The DNNs are based on predictive coding theory, which assumes that the internal models of the brain predict the visual world at all times and that errors between the prediction and the actual sensory input further refine the internal models.

In this research, the DNNs were trained with natural scene videos of motion from the point of view of the viewer, and the motion prediction ability of the obtained computer model was verified using a rotating propeller in unlearned videos and the 'Rotating Snake Illusion.'

Mel Goodale - ‘Visual Routes to Knowledge and Action: (almost) 25 Years of Two Visual Systems’

Traditionally, research on vision focused on its role in perception and our cognitive life. Except for the study of eye movements, which have typically been ...

Lecture 16 | Adversarial Examples and Adversarial Training

In Lecture 16, guest lecturer Ian Goodfellow discusses adversarial examples in deep learning. We discuss why deep networks and other machine learning ...


Please support Peter Joseph's new, upcoming film project: "InterReflections" by joining the mailing list and helping: LIKE ..

Google I/O'17: Channel 2

Technical sessions and deep dives into Google's latest developer products and platforms.

Making an interactive drawing manual with articy:draft