Model-based Thinking in Machine Learning
The unexpected guide to moving beyond common curve-fitting, 10x'ing ML skill development, and becoming an AI creative
Break out of the mentality curve-fitting, overthinking training, and under-thinking how the data is generated.
Deconstruct your biases, and acquire new mental models for applied data science and machine learning.
With this module we perform this mental refactoring. We will graft on a high-level understanding of causality on the a foundation of deep generative machine learning.
Relationship to other modules
- This is module 1/2 in Refactored Thinking for Machine Learning and Causality
- This is module 1/2 in Causal Modeling in Machine Learning Track
However, if you were to stop after completing this module, you would walk away with solid experience in causal modeling using deep generative machine learning.
Robert didn't start in machine learning. He started his career by becoming fluent in Mandarin Chinese and moving to Tibet to do developmental economics fieldwork. He later obtained a graduate degree from Johns Hopkins School of Advanced International Studies.
After switching to the tech industry, Robert's interests shifted to modeling data. He attained his Ph.D. in mathematical statistics from Purdue University, and then he worked as a research engineer in various AI startups. He has published in journals and venues across these spaces, including RECOMB and NeurIPS, on topics including causal inference, probabilistic modeling, sequential decision processes, and dynamic models of complex systems. In addition to startup work, he is a machine learning professor at Northeastern University.