Tag: null space

Congratulations to Dr. Matthew Cook for successfully passing his PhD dissertation exam! Dr. Cook’s research centers on developing algorithms that use null space projections within neural networks to add additional functionality. The primary application of this method is detecting out-of-distribution data, such as encountering unexpected objects during Automatic Target Recognition data collections. Moreover, results showed […]

Congratulations to our labmates, Matt Cook, Alina Zare and Paul Gader for presenting at the 37th International Conference on Machine Learning (ICML) Workshop on Uncertainty and Robustness in Machine Learning! Their paper, titled “Outlier Detection through Null Space Analysis of Neural Networks”, introduces a novel method for detecting outliers in a set of data. Matt will […]

Abstract: Many machine learning classification systems lack competency awareness. Specifically, many systems lack the ability to identify when outliers (e.g., samples that are distinct from and not represented in the training data distribution) are being presented to the system. The ability to detect outliers is of practical significance since it can help the system behave […]