2024 FFT

Old is new again: Applied harmonic analysis and interpretable AI

Emily King (CSU)

Abstract: Although neural networks yield powerful results in many applications, there are drawbacks to their use. For example, there are many fields where the amount of labeled data needed to train neural networks is insufficient (i.e., in the realm of un- and semi-supervised learning). Further, the internal decision-making process of a neural network is often opaque, leading to a desire for more interpretable techniques. These concerns have led some to take another look at algorithms built on more classical mathematics, like harmonic analysis. Even when using neural networks, it is useful to consider lessons learned from harmonic analysis. A number of buzz words from machine learning and their connections to harmonic analysis will be presented.