Machine Learning is, put simply, getting computers to generalize from examples. And that's what I try to do: put [seemingly complicated] things simply. My posts on Machine Learning (ML) consist primarily of beginner-focused introductions to common ML models or concepts. I felt like too many ML tutorials weren't accessible enough, so I strove to make my guides as clear and beginner-friendly as possible.
Unsure where to start? Here are some of my best / most popular posts:
What Information Gain and Information Entropy are and how they're used to train Decision Trees.Read
A simple walkthrough of deriving backpropagation for CNNs and implementing it from scratch in Python.Read
A simple guide to what CNNs are, how they work, and how to build one from scratch in Python.Read
What Gini Impurity is (with examples) and how it's used to train Decision Trees.Read
A simple explanation of how they work and how to implement one from scratch in Python.Read
Why existing libraries are uninspiring and how I built a better one.Read