EurekAlert: Researchers unveil tool to debug ‘black box’ deep learning algorithms

Eurekalert: Researchers unveil tool to debug ‘black box’ deep learning algorithms. “Deep learning systems do not explain how they make their decisions, and that makes them hard to trust. In a new approach to the problem, researchers at Columbia and Lehigh universities have come up with a way to automatically error-check the thousands to millions of neurons in a deep learning neural network. Their tool, DeepXplore, feeds confusing, real-world inputs into the network to expose rare instances of flawed reasoning by clusters of neurons. Researchers present it on Oct. 29 at ACM’s Symposium on Operating Systems Principles in Shanghai.”