Skip to content

juaml/General_Machine_Learning

Repository files navigation

🚀 General Machine Learning

Welcome to the "General Machine Learning" course! 🎉 Whether you're a researcher, student, or data enthusiast, this course will equip you with essential machine learning concepts, from foundational principles to advanced evaluation techniques.

📅 Course Details

  • Dates: May 21, 2025 – Juli 04, 2025
  • Time: Wednesdays, 15:00 – 17:00
  • Location: Virtual (Zoom link provided)
  • Prerequisites: Basic Python & statistics knowledge recommended

🧠 What You'll Learn

This course covers core ML concepts and practical techniques to build robust models. By the end, you'll:

  • 📊 Understand ML fundamentals – features vs. targets, linear/non-linear models, and hyperparameter tuning
  • ⚖️ Master model evaluation – train-test splits, cross-validation, and metrics for performance assessment
  • 🔍 Reduce dimensionality – tackle the curse of dimensionality with PCA and feature selection
  • 🤖 Interpret models – analyze biases, SHAP/LIME explanations, and model's weights
  • 🚫 Prevent data leakage – identify and mitigate leakage types for reliable models
  • ⚠️ Handle imbalanced data – address class imbalance, missing values, and confounds

📚 Detailed Content

Machine Learning Basics

  • Core principles, real-world applications, and feature/target relationships
  • Linear vs. non-linear models and hyperparameter optimization

Model Selection & Evaluation

  • Train-test splits, K-fold CV, nested CV, and stratification
  • Evaluation metrics for different contexts

Dimensionality Reduction & Feature Engineering

  • Curse of dimensionality, feature selection (reverse/forward), and PCA
  • Data normalization for scalable performance

Model Interpretability

  • Analyzing SVM weights, detecting biases, and SHAP/LIME explanations

Data Leakage, Confounds and Imbalance data

  • Types of leakage (test-to-train, feature-to-target) and mitigation strategies
  • Handling imbalanced data, missing values, and confounds

🔗 Resources

🔗 Full Program: Google Doc
📂 Slides & Materials: Sciebo

👨‍💻👩‍💻 See you in class! Happy learning! 👨‍💻👩‍💻

About

General Machine Learning

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 2

  •  
  •