Using artificial intelligence to find anomalies hiding in massive datasets

Researchers at the MIT-IBM Watson AI lab have developed a computationally efficient method that could be used to identify anomalies in the U.S. power grid in real time. The novel technique augments a special type of machine-learning model with a powerful graph structure, and does not require any labeled data to train.

Related Keywords

Jie Chen ,Enyan Dai ,International Conference On Learning Representations ,Watson Ai Lab ,Pennsylvania State University ,Us Department Of Energy ,Pennsylvania State ,International Conference ,Mit Ibm Watson Ai Lab ,Ormalizing Flow Models ,