Learn machine learning — classical models first, deep learning second.

Strive builds an ML course that earns each technique before reaching for the next — regression and classification, then trees and ensembles, then a careful look at deep learning. Hands-on with scikit-learn, lessons stream live with runnable code, and the recall queue keeps the math and the APIs in working memory.

What you’ll learn

• Frame a problem as supervised, unsupervised, or "probably not ML at all".
• Train, tune, and interpret linear and logistic regression beyond plug-and-pray.
• Use decision trees, random forests, and gradient boosting where they earn their keep.
• Evaluate models honestly — cross-validation, the right metric, and the right baseline.
• Diagnose bias, variance, leakage, and class imbalance — and fix them.
• Engineer features that beat fancier models on real-world data.
• Read a deep-learning paper without panicking and run a small PyTorch model.

A typical Strive course on Machine learning

1. When ML is the answer — and when it isn’t3 lessons
2. Linear and logistic regression — beyond plug-and-pray5 lessons
3. Decision trees, random forests, and gradient boosting5 lessons
4. Honest evaluation — cross-validation, metrics, baselines4 lessons
5. Bias, variance, leakage, and class imbalance4 lessons
6. Feature engineering that beats fancier models3 lessons
7. A glance at deep learning — a small PyTorch project3 lessons

Demonstration outline — your course is generated around your answers, so module count, depth, and difficulty will differ from this. Across the 7 modules above there are 27 lessons.

Frequently asked