Example of Differential Testing for Deep Learning Systems (IMAGE)

Columbia University School of Engineering and Applied Science

Example of Differential Testing for Deep Learning Systems

Caption

A debugging tool developed by researchers at Columbia and Lehigh generates real-world test images meant to expose logic errors in deep neural networks. The darkened photo at right tricked one set of neurons into telling the car to turn into the guardrail. After catching the mistake, the tool retrains the network to fix the bug.

Credit

Columbia Engineering

Usage Restrictions

None

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.