|Friday, February 16|
|CS11 Data Mining Algorithms||
Fri, Feb 16, 2:00 PM - 3:30 PM
Deep Neural Networks for Scalable Prediction (303533)
Keywords: Deep Neural Networks, AI, prediction, classification, machine learning
Recent, significant advances in the development of methods for applying complex (‘deep’) artificial neural networks (DNN’s) to important problems are yielding fruit in many settings. DNNs are being used on large volumes of data to provide solutions in areas including natural language processing, image processing, speech recognition, and autonomous vehicle navigation. Nontrivial DNN applications by practitioners have become more than just barely feasible because of the availability of powerful computing hardware and open source neural network software. This talk will summarize the fundamentals of applying deep neural networks. It will explain the important design and execution decisions to be made when applying them, and it will review open source tools and code resources available to practitioners. Finally, it will illustrate the use of DNN’s by describing from start to finish a real application for predicting consumer behavior.