Free · No credit card
You've been told to build a BDT.
Start here — free.
Get Module 1 of the course (Introduction to ML for Physicists) plus a one-page roadmap: the exact path from zero to a validated classifier, and the 5 mistakes that get analyses bounced in review.
Two files, straight to your inbox
📘 Module 1 Workbook — Introduction to ML for Physicists
The actual first module of the course. ML vocabulary mapped to physics you already own: features are observables, the bias–variance trade-off is the tension you manage every time you pick a fit's degrees of freedom, and your χ² fit is already a model.
🗺️ The BDT Roadmap (one page)
The six stages from zero to a publication-ready classifier — orient, frame, build, boost, apply, validate — plus the five mistakes reviewers check for every time (overtraining, data/MC disagreement, train/measure overlap, biased cut optimisation, unpropagated systematics).
Sound familiar?
Your supervisor said "use a BDT for your analysis." You've spent weeks across 15 GitHub repos, three TMVA tutorials, and a 200-page ROOT manual. Your ROC curve still looks wrong, and the review committee meets in a few months.
You don't need another lecture recording or another scattered notebook. You need the path — in order — and someone to name the pitfalls before you fall into them.
The science is the proof
Boosted decision trees are not a fashion. They outperform rectangular cuts on multivariate classification in high-energy physics, improving signal efficiency by roughly 30–50% at equal background rejection (Roe et al., NIM A 543 (2005) 577–584). Gradient boosting consistently ranks among the top classifiers on HEP benchmarks, including the HiggsML challenge (Chen & Guestrin, KDD 2016; Adam-Bourdarios et al., JMLR W&CP 42 (2015)).
Start with the free Module 1 and the roadmap. If it clicks — and for most physicists it does — you'll know exactly where to go next.
Get your free copy now
Ready to go the whole way?
The free Module 1 gets you oriented. The complete course walks all six stages end-to-end — from first principles to a classifier your review committee signs off on.
See the Complete Course — $97 →