"Researchers Unveil Tool to Debug 'Black Box' Deep Learning Algorithms"

Self-driving cars operate through the use of deep learning systems. Deep learning is a form of machine learning that uses layers of artificial neurons in an attempt to mimic the processing and merging of information performed by the human brain. Although this technology has improved significantly in the development of intelligence, increased automation of tasks still raise concerns pertaining to safety, security, and ethics. A tool by the name of DeepXplore has been developed by researchers at Columbia and Leigh universities to perform automatic error-checking of neurons within deep learning neural networks used by self-driving cars to uncover deficient reasoning by clusters of neurons, malware masqueraded as harmless code in anti-virus software, and more. This article further discusses the concerns surrounding deep learning systems, the DeepXplore tool, and other methods of debugging the neural networks in self-driving cars. 

EurekAlert! reports "Researchers Unveil Tool to Debug 'Black Box' Deep Learning Algorithms"