Deep Neural Network Regression at Scale in Spark MLlib – Jeremy Nixon
Deep Neural Network Regression at scale in Spark MLlib – Jeremy Nixon will focus on the engineering and applications of a new algorithm in MLlib. The presentation will focus on the methods the algorithm uses to automatically generate features to capture nonlinear structure in data, as well as the process by which it’s trained. Major aspects of that are the compositional transformations over the data, advantages of the various activation functions, the final linear layer, the cost function and training via backpropagation. Applications will look into how to use neural network regression to model data in computer vision, finance, and the environment. Details around optimal preprocessing, the type of structure that can be found, and managing its ability to generalize will inform developers looking to apply nonlinear modeling tools to problems that they face.