Machine Learning: 2017 Edition
Course Materials
This course is being taught by Jeremy Howard, and was developed by Jeremy along with Rachel Thomas. Jeremy used a top-down teaching method, which is different from how most math courses operate. If you took the fast.ai deep learning part 1 2018 edition course, that is what we used. The course used a specific library (fastai) built on top of PyTorch. The first part of the course focused on Decision Trees with Random Forests, the second part on Neural Networks for Deep Learning. The course goes at a somewhat gentler pace, but doesn't show how to build world-class models (the focus is more on process and interpretation, and also more in depth discussion of foundational details). The Deep Learning course is more intense, and gets you building state of the art models from lesson 1. Both can be understood on their own, but they both support each other.
Lessons Cover
- Introduction to Random Forests
- Random Forest Deep Dive
- Feature Engineering
- Random Forest Interpretation
- Train vs Test
- What is Machine Learning
- Why Do We Use Machine Learning
- Decision Trees Ensemble
- Basic Neural Networks
- SGD
- Backpropagation
- Neural Networkwork Training
- Broadcasting
- PyTorch
- Logistic Regression
- Natural Language Processing (NLP)
- Naive Bayes
- Structured and Time-Series Data
- Entity Embeddings
- Data Science and Ethics