Abstract: Statistics and statistical inference form the core of making sense of data. Inference is what allows us to extrapolate and generalize from our data to the populations we are trying to understand. Below inference lies measurement, how we attach numbers to phenomena we'd like to understand. In this tutorial we consider measurement and inference, especially as it pertains to scientific repeatability. We pay particular focus on using artificial intelligence and machine learning as methods of measurement and the fundamental role that inference plays. Specifically, we focus on validation.
1. What is statistical inference?
2. Measurement foundations.
3. Scientific repeatability and reproducibility.
4. Inference for ML and AI.
After this sessions students will have:
1. A basic understanding of statistical inference including generalizability.
2. A basic understanding of the role that inference plays in validating ML and AI.
3. Techniques to apply to understand reproducible and replicability.
4. Understand statistical sampling assumptions and how they factor into summary measures.
Basic data science facility. Basic algebra and a small amount of statistics.
Bio: Babak is a Data Scientist currently working as a postdoctoral fellow at Johns Hopkins University. His professional journey spans various domains, including App development, Ed-Tech Development and Research, Biological Computing, High Density Neuro-computing, and Neuro-Imaging. His overarching goal is to proactively contribute to innovative solutions and cultivate data-driven decision-making processes. Babak holds a PhD in Biomedical Engineering from Arizona State University, complemented by an MS in Polymer Engineering.