Course Detail

Bayes, AI and Deep Learning (41916)

Course Description by Faculty

  • Polson, Nicholas
  • Content
    This course focuses on the applications of data analytic, machine learning and deep learning methods. We will start with a quick review of basic Bayesian models followed by tools and concepts from artificial intelligence. Students will learn how to use deep learning to analyze a variety of complex real world problems. Numerous empirical examples from finance, internet analytics, and sports are used to illustrate the material covered. Google’s development of deep neural networks and applications will be discussed in detail.

    Emphasis will be placed on understanding concepts of Bayes, AI and Deep Learning. The three main topics covered are: (i) Bayesian methods including conditional probability,hierarchical models (ii) Artificial Intelligence including modern regression methods such as lasso and ridge regression. Dimensionality reduction techniques and sparsity are central to data analysis (ii) Deep Learning including Neural Nets, Architecture design,Stochastic Gradient Descent, speeding up convergence. Throughout business and internet applications including machine intelligence, reinforcement learning, image and speech recognition will be used to illustrate the wide range of applications.

  • No Syllabus Available
  • Autumn 2021Section: 41916-50TH 8:30AM-11:30AMHarper Center3SW - Seminar RoomIn-Person Only
Description and/or course criteria last updated: June 24 2021