A practical weekly series teaching Automated Machine Learning from scratch — through the lens of human reinvention. Every concept, every algorithm, every pipeline stage mapped to something real. Something you've already lived.
Automated Machine Learning (AutoML) automates the process of selecting, training, and optimising machine learning models. But look closely at its pipeline, and you'll find something startling: it is a near-perfect map of human reinvention.
Each episode teaches a real AutoML concept — from data ingestion to deployment — with working examples, clear explanations, and no prerequisites assumed.
Every technical concept is anchored in lived experience. Preprocessing isn't just data cleaning — it's the work of honest self-reflection. Training isn't just iteration — it's showing up every day.
Whether you're pivoting careers, rebuilding confidence, or simply refusing to stay the same — this series is for you. No machine learning background needed.
Every episode builds on the last. By the end of the series, you'll have a working understanding of the full AutoML pipeline — and a new vocabulary for your own growth journey.
I'm Dr. Tertsegha Joseph Anande — PhD in Computing, ML Researcher, and Lecturer at QAHE/Ulster University in Birmingham. I specialise in Machine Learning, AutoML, Ensemble Learning, and Cyber-Physical Security.
On paper, things look fine. But somewhere along the way, I noticed something quietly slipping away. The drive. The hunger. That inner restlessness that once pushed me to pursue more, build more, become more. It didn't vanish overnight — it was more gradual than that. Life happened. Responsibilities stacked up. And before I knew it, adulthood had swallowed up the very passion that once defined me.
I was still showing up. Still completing tasks. Still functioning. But I was doing tomorrow what I did today, and today what I did yesterday. The zeal to aspire — to reach for the next exploit — had gone quiet.
That silence was louder than anything else. That's when I decided: maybe it's time to apply the principles of how machines learn and adapt — to myself.
"What if there's still more?"