# Machine learning foundations

Source: https://freeaicourses.com/paths/ml-foundations

## Steps

### Step 1: Kaggle Intro to Machine Learning

A fast, practical on-ramp if you haven't done it yet.

You understand the basic training and validation workflow.

### Step 2: Machine Learning Crash Course

Fills in the concepts properly, with excellent interactive visuals.

You can explain loss, gradient descent and overfitting.

### Step 3: CS50's Introduction to AI with Python

Builds the algorithms by hand, so nothing is a black box.

You can implement core ML and search algorithms from scratch.

## Related pages

- [Kaggle Intro to Machine Learning](https://freeaicourses.com/courses/kaggle-intro-machine-learning)
- [Machine Learning Crash Course](https://freeaicourses.com/courses/machine-learning-crash-course)
- [CS50's Introduction to AI with Python](https://freeaicourses.com/courses/cs50-ai)
- [Deep learning, hands-on](https://freeaicourses.com/paths/deep-learning)
- [AI learning paths free to follow](https://freeaicourses.com/paths)
- [All free AI courses, rated](https://freeaicourses.com/courses)
- [AI learning path for non-coders](https://freeaicourses.com/paths/ai-for-non-coders)
- [Use AI tools well at work](https://freeaicourses.com/paths/ai-at-work)
- [Python for AI, from zero](https://freeaicourses.com/paths/python-for-ai)
- [The maths ML actually uses](https://freeaicourses.com/paths/maths-for-ml)
- [Build apps with LLMs](https://freeaicourses.com/paths/build-with-llms)
- [Become an ML engineer](https://freeaicourses.com/paths/ml-engineer)
- [From data analysis to AI](https://freeaicourses.com/paths/data-science-to-ai)
- [Kaggle Learn](https://freeaicourses.com/platforms/kaggle)
- [Google](https://freeaicourses.com/platforms/google)
- [Harvard CS50](https://freeaicourses.com/platforms/harvard-cs50)