Artificial neural networks power the recent advances in computer vision, speech recognition, and machine translation. This is a first course on neural networks with a focus on applications in computer vision and natural language processing. Topics will include generic feedforward neural networks, convolutional neural networks for computer vision tasks, and recurrent neural networks with application to natural language processing, with other topics to be selected based on the interests of the instructor and the class. Prereq: MATH 425, MATH 545 or MATH 645, COMP 490, or permission of the instructor. Also listed as COMP 750.

In this class, students will build their foundational toolbox in data science: upon completion, students will be able to use the computer from the command line; practice version control with GIT & GitHub; gain a mastery of programming in Python; data wrangling with Python and perform an exploratory data analysis (EDA) in Python. All learning objectives are achieved through active application of these techniques to real world datasets. Pre- or Coreq: DATA 800.

In this class, students will learn foundations of practical machine learning: upon completion, students will be able to understand and apply supervised and unsupervised learning in Python to build predictive models on real world datasets. Techniques covered include (but not limited to): preprocessing, dimensionality reduction, clustering, feature engineering and model evaluation. Models covered include: generalized linear models, tree-based models, bayesian models, support vector machines, and neural networks. All learning objectives are achieved through active application of these techniques to real world datasets. Prereq: DATA 800; DATA 820 Pre- or Coreq: DATA 821.

This is the second of a two course self-designed thesis sequence offered under the master's of science degree in analytics. The nature of the class is applied learning directly around a student directed analytic thesis project. The class requires competency in two areas for the successful completion of the course. Students will have completed the data collection, cleaning and management and created readable analytic files for the project of their choice in the first of the two course sequence. Students are primarily responsible to apply modern analytical tools and techniques like predictive modeling, segmentation, and network analysis etc. They are also required to write a formal 2000+ word report on the findings of the project. The report is expected to include modern data visualization synthesized with analysis results. Prereq: DATA 803.