INDUSTRIAL AND APPLIED DATA SCIENCE – THEORY AND PRACTICE

Credit Hours: 2 · Graduate

This graduate-level course presents a pragmatic introduction to the foundational theory of data science along with a series of practical skills for working data scientists. It includes modern aspects of data science driven by massively more data and computer power such as deep neural networks, reinforcement learning and the principles of generative AI. The course is supplemented by practical programming exercises to be completed every week by all students. Industrial-strength applications of data science in the energy sector, from image and text processing to physics-based simulations are discussed in appropriate detail, along with how the enterprise value gets delivered in practice. How does data science relate to MLOps, how do data science teams work, how quickly will skillsets need updating? Recommended Prerequisite(s): Equivalent of advanced course work in computer programming (e.g. COMP 321 ), calculus (e.g. MATH 212 ), statistics or probability theory, linear algebra (e.g. CAAM 334 or CMOR 303 or CAAM 335 or CMOR 302 ). Proficiency in MATLAB (course programming language) or Python (alternative to MATLAB available to course participants).