In this video, learn how to access the course exercise files and explore how they are set up.
- [Instructor] You will have access to all the exercise files for this course so you can just follow along yourself, and I highly recommend you do so. Particularly when it comes to learning through code, there's no substitute for actually writing the code and debugging it yourself. So I highly encourage you to use the notebooks, write the code, tweak the code, see how it changes things. Even purposely break it so that you can understand the bounds, and why it may or may not work. So the exercise files are organized into folders, one for each chapter. Each chapter folder is organized into individual lessons. Within each lesson, you'll notice that there is a start folder and an end folder. The start folder is the notebook that you should start coding in, and the end folder will contain the completed notebook just for reference. We're only using one dataset for this entire course. You'll find that included as well. So you can run the notebooks exactly as they are. Let's go ahead and launch one of these jupyter notebooks. So you can just jump over to the terminal, you'll want to navigate to wherever these notebooks live, and then all you have to do is just enter the jupyter notebook command, and that'll launch notebook right in your browser. And you can navigate to any of these folders that you saw previously in this file structure. So now that you know what tools you need and how you access them, let's get started.
- What is machine learning (ML)?
- ML vs. deep learning vs. AI
- Handling common challenges in ML
- Plotting continuous features
- Continuous and categorical data cleaning
- Measuring success
- Overfitting and underfitting
- Tuning hyperparameters
- Evaluating a model