Abstract：achine learning has played an important role in particle physics for simulation, reconstruction, and analysis for decades. The emergence of deep learning and new heterogeneous computing paradigms are transforming almost every aspect of the software in particle physics into Machine Learning approaches. I will provide an overview of how machine learning is used in the LHC experiments, followed by an introduction to the core concepts of deep learning, connections between deep learning and LHC data analysis, examples of key results, deployment of deep learning in particle physics computing platforms, and discussion of future prospects and concerns. I will demonstrate that the acceleration of machine learning inference as a web service represents a heterogeneous computing solution for particle physics experiments that potentially requires minimal modification to the current computing model. Our code and data are publicly available athttps://fastmachinelearning.org.