Particle physics involves an intense data science challenge: signals of
interest, like for the Higgs boson are often buried in backgrounds
trillions of times as large. Over the last decade or so, there has been
a revolution in machine learning, and over the last year or two, the
revolution has started to influence collider physics. For example, image
recognition technology based on convolutional neural networks can be
used to find patterns in the distribution of energy around a detector.
Or recurrent neural networks designed for natural language processing
can be applied to parse the substructure of jets. This talk will review
some of these developments and discuss some exciting possibilities for
the future.