Automatic Differentiation and Deep Learning

<!--HTML--><p>Statistical learning has been getting more and more interest from the particle-physics community in recent times, with neural networks and gradient-based optimization being a focus.</p> <p>In this talk we shall discuss three things:</p> <ul> <li>automatic differention tools: tools to quickly build DAGs of computation that are fully differentiable. We shall focus on one such tool "PyTorch".</li> <li>&nbsp;Easy deployment of trained neural networks into large systems with many constraints: for example, deploying a model at the reconstruction phase where the neural network has to be integrated into CERN's bulk data-processing C++-only environment</li> <li>Some recent models in deep learning for segmentation and generation that might be useful for particle physics problems.</li> </ul>