Term 1 Program Structure

Term 1 of the Machine Learning Nanodegree Program is divided into four parts, giving you a thorough understanding of machine learning, and covering some of the major topics.

After you've completed the first term of the program, you'll be able to enroll in Term 2 for an additional $999 where you'll learn deep learning, reinforcement learning, and complete your personal capstone project all with the support of Udacity's mentors and expert reviewers. You'll then receive your Machine Learning Nanodegree graduation certificate after you have completed both terms!

But first, here are the 4 sections in Term 1:

Machine Learning Foundations

In this section, you'll get an overview of the main algorithms of machine learning. In a few fun bite-sized lectures you'll get to see how they work, and how they get applied to some real life problems. Then, you'll get to test yourself with a mini-project, where you'll learn to detect spam in e-mails based on the text inside the e-mail.

Model Evaluation and Validation

In this section, you'll learn the basics of how to build machine learning models. In a nutshell, we'll be answering the following questions:

• How do I train a model?
• How do I know if the model is good?
• How do I improve this model?

First we'll start with teaching you how to train and test models using sklearn. Then, we'll go over the main metrics used for evaluating models, such as accuracy, precision, recall, etc. After that, we'll go over the main problems that a model may have, such as overfitting and underfitting, and we'll learn methods to overcome these difficulties, and to really improve your models.

Supervised Learning

Now we're ready to learn the main algorithms of supervised learning. In this section, we'll learn the main ones, including linear and logistic regression, decision trees, naive Bayes, neural networks, and support vector machines. We'll also learn to combine these algorithms to achieve their full potential, in the ensemble methods section. Every section is equipped with a lab, where you'll get to apply your knowledge using sklearn.

Unsupervised Learning

In this section we'll be going over the main unsupervised learning algorithms, including several clustering methods, and dimensionality reduction. You'll go through several mini-projects and labs in which you'll be able to apply these concepts with real data.