Abstract
A revolution is underway in which deep neural networks are routinely used to solve diffcult problems such as face recognition and natural language understanding. Particle physicists have taken notice and have started to deploy these methods, achieving results that suggest a potentially significant shift in how data might be analyzed in the not too distant future. We discuss a few recent developments in the application of deep neural networks and then indulge in speculation about how such methods might be used to automate certain aspects of data analysis in particle physics. Next, the connection to Bayesian methods is discussed and the paper ends with thoughts on a significant practical issue, namely, how, from a Bayesian perspective, one might optimize the construction of deep neural networks.
Highlights
The idea that artifacts could somehow be endowed with human-like intelligence has a long history measured in centuries
We focus on a class of machine learning methods, namely deep neural networks (DNN), which underlies many recent successful applications of machine learning on real-world problems
We start with a discussion of some recent successful applications of deep neural networks and follow with some thoughts about what kinds of applications of deep learning might be possible in experimental particle physics
Summary
The idea that artifacts could somehow be endowed with human-like intelligence has a long history measured in centuries. Understanding of the promised feats of artificial intelligence, including the many already in routine use, is enhanced by recognizing that current applications and those in the foreseeable future are “merely” approximations of well-defined mathematical quantities, probabilities. After some transformations to remove distortions, the machine-based algorithm has to distinguish characters from other elements of the picture We start with a discussion of some recent successful applications of deep neural networks and follow with some thoughts about what kinds of applications of deep learning might be possible in experimental particle physics. We continue with a discussion of the connection between deep learning and Bayesian methods and how one might go about optimizing one important aspect of the training of deep neural networks.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
