Explainable AI for High Energy Physics
This addresses the black-box problem in neural networks for high energy physics researchers, but it is incremental as it proposes using existing xAI methods in this domain.
The paper explores applying explainable AI (xAI) methods to neural networks in high energy physics to make them interpretable by establishing quantitative input-output relationships, but it does not report specific results or numbers.
Neural Networks are ubiquitous in high energy physics research. However, these highly nonlinear parameterized functions are treated as \textit{black boxes}- whose inner workings to convey information and build the desired input-output relationship are often intractable. Explainable AI (xAI) methods can be useful in determining a neural model's relationship with data toward making it \textit{interpretable} by establishing a quantitative and tractable relationship between the input and the model's output. In this letter of interest, we explore the potential of using xAI methods in the context of problems in high energy physics.