The MicroBooNE experiment consists of a liquid argon time-projection chamber (LArTPC) that sits 470 m from the origin of the Booster Neutrino beam at Fermi National Lab. The goal of the experiment is to advance our knowledge of neutrino-nucleus cross sections and shed light on the MiniBooNE low energy anomaly. The latter is one of several anomalies seen in neutrino oscillation experiments that have been interpreted as hints for non-standard neutrinos. I will discuss the status of MicroBooNE and some of its achievements after one year of data taking. In particular, I will focus on one effort to use convolutional neural networks (CNNs) to reconstruct and select neutrino events. CNNs, a type of machine learning algorithm, are often the state-of-the-art approach in many computer vision tasks. For example, CNNs have found applications ranging from automated human face recognition to real-time object detection for self-driving cars. I’ll describe our first steps in applying CNNs to the task of analyzing neutrino events in LArTPCs.