Duke team disentangles neural networks to understand how they see the world (IMAGE)

Duke University

Duke team disentangles neural networks to understand how they see the world

Caption

New research offers clues to what goes on inside the minds of machines as they learn to see. A method developed by Cynthia Rudin's lab reveals how much a neural network calls to mind different concepts as an image travels through the network's layers.

Credit

Courtesy of Zhi Chen, Duke University

Usage Restrictions

Please credit Zhi Chen, Duke University

License

Licensed content

Disclaimer: AAAS and EurekAlert! are not responsible for the accuracy of news releases posted to EurekAlert! by contributing institutions or for the use of any information through the EurekAlert system.