The purpose of this course topic is to familiarize broad audiences of students from science and engineering into Artificial Intelligence (AI) and Machine Learning (ML) and encourage them to design their own data science workflow for a given real-life application. Students will learn how different data structures and data types are generated and handled from different acquisition modalities for the purpose of AI/ML development. Formats of Continues versus discrete data will be discussed in multi-dimensional structure. Different applications in real-world examples will be introduced such as in engineering, medicine, and science. Techniques of pre-processing for cleansing the data and their preparation will be introduced. Data management systems will be discussed and explained how to handle big data storage and communication. Post-processing techniques such as QA measures, enhancements methods, augmentation, dimensionality reduction, visualization of data for locally vs globally distributed data will be discussed.

Prerequisites:

• Multivariable Calculus
• Preliminaries in Linear Algebra
• Preliminaries in Statistics
• Preliminaries in Signal Processing and Analysis