Grokking Machine Learning
I am the author of Grokking Machine Learning, a book by Manning Editors. This is a book in which I explain the main algorithms and techniques of supervised learning in a very friendly and intuitive way that doesn’t require heavy mathematics or coding.
The book has code in Python, Numpy, Pandas, Scikit Learn, and PyTorch. You can find it in this repo.
With this promo code: serranoyt, you’ll get a 40% discount in the book!
- What is machine learning?
- Types of machine learning
- Drawing a line close to our points: Linear regression (code)
- Optimizing the training process: Underfitting, overfitting, testing, and regularization (code)
- Using lines to split our points: The perceptron algorithm (code)
- A continuous approach to splitting points: Logistic classifiers (code)
- How do you measure classification models?: Accuracy and its friends
- Using probability to its maximum: The Naive Bayes model (code)
- Splitting data by asking questions: Decision trees (code)
- Combining building blocks to gain more power: Neural networks (code)
- Finding boundaries with style: Support vector machines and the kernel method (code)
- Combining models to maximize results: Ensemble learning (code)
- Putting it all in practice: A real life example of data engineering and machine learning (code)
- Appendix A: Solutions to exercises
- Appendix B: The math behind gradient descent
- Appendix C: References
The book has coding labs and exercises to accompany it. The Github repo is here.
The official errata for the book can be found here. I maintain my own unofficial errata page here.