Data Analysis, Design of Experiment, and Machine Learning

Explore comprehensive statistical analysis and machine learning concepts through this 11-hour video lecture series from Purdue University's ECE 695 course taught by Ashraf Alam. Build foundational knowledge in modern statistical concepts and tools for analyzing experimental and simulation-generated data while mastering principles of experimental design to ensure statistical relevance and utility. Learn to distinguish between big and small data sources, apply robust data collection and plotting techniques, and understand the differences between physical and empirical distributions. Master model selection criteria and goodness of fit assessments, then advance to scaling theory and statistical theory of experimental design. Develop expertise in bootstrap methods, cross-validation techniques, and statistical design of experiments including Taguchi methods and ANOVA analysis. Gain proficiency in principal component analysis before progressing to machine learning fundamentals, deep learning concepts, and physics-based machine learning approaches. Acquire practical skills using MATLAB and Excel tools for data analysis and interpretation across 15 comprehensive lectures covering topics from basic statistical review through advanced machine learning applications, concluding with future outlook and applications in engineering and scientific research.