ML Training & Evaluation Guidance

I’m looking for a mentor who can help me grasp core machine-learning concepts with a strong emphasis on how models are trained, validated, and ultimately judged. My immediate goal isn’t to build an app or optimise a production pipeline; instead, I want to understand the fundamentals well enough to make confident, informed decisions when I start tackling real-world projects later on.

Here’s what I need:
• A clear, structured learning path that walks me through the full training workflow—data splits, cross-validation, hyper-parameter tuning, and model selection—using Python and libraries such as scikit-learn (with room to branch into TensorFlow or PyTorch once the basics are solid).
• Practical explanations of evaluation metrics—accuracy, precision, recall, F1, ROC AUC—and when each one matters.
• Short coding exercises or notebooks after each session, plus feedback on my solutions so I can correct mistakes quickly.
• Live voice or video sessions (screen-sharing friendly) where I can ask questions in real time, ideally once or twice a week.

By the end of our engagement I should be able to:
– Design an experiment that avoids leakage and overfitting.
– Choose sensible metrics for different problem types.
– Interpret learning curves and adjust training procedures accordingly.

If you’re patient, enjoy teaching beginners, and have solid hands-on experience with modern ML tooling, I’d love to hear how you would structure our time together and what materials you would provide.