| Abstract: |
Machine learning techniques developed in computer science are increasingly applied to problems in particle physics. One such fundamental problem is the binary discrimination of signal events from background, and machines have demonstrated impressive performance, often exceeding that of techniques designed by humans for the same problem. Nevertheless, what physics the machine exploits to do this remains mysterious. In this talk, I will discuss our recent efforts to open the black box and understand what the machine learns, which in turn can inform how to improve machine learning. |
