Hands-on: Getting Started
It's easiest to jump in and get your hands dirty by building small projects in Python. Python already has supporting frameworks and libraries that makes it easier to enter the ML world.
Python Frameworks
Python Frameworks for building ML models
- Scikit-learn - very easy to use, implements many machine learning algorithms efficiently, so it makes for a great entry point to learning machine learning.
- Tensorflow - a more complex library for distributed numerical computation. It makes it possible to train and run very large neural networks efficiently by distributing the computations across potentially hundreds of multi-GPU (graphics processing unit) servers.
- Keras - a high-level deep learning API that makes it very simple to train and run neural networks. Keras comes bundled with TensorFlow, and it relies on TensorFlow for all the intensive computations.
Data Manipulation libraries
Python’s main scientific libraries
Resources
- Library tutorials - Google Colab, Aurélien Geron
- Scikit-learn user guide