Play by Play: Machine Learning Exposed
In this course, you’ll explore machine learning topics, such as supervised learning, unsupervised learning, reinforcement learning, and deep learning.
What you'll learn
Play by Play is a series in which top technologists work through a problem in real time, unrehearsed, and unscripted. In this course, Play by Play: Machine Learning Exposed, James Weaver and Katharine Beaumont will start with the basics, and build up in an approachable way to some of the most interesting techniques machine learning has to offer. Explore Linear Regression, Neural Networks, clustering, and survey various machine learning APIs and platforms. By the end of this course, you'll get an overview of what you can achieve, as well as an intuition on the maths behind machine learning.
Table of contents
- Types of Supervised Learning Problems: Regression and Classification 10m
- Anatomy and Visualizing Artificial Neural Networks 16m
- Forward Propagation 11m
- Back Propagation 8m
- Speed Dating Example 7m
- Evaluating and Optimizing a Neural Network 12m
- Regression Sum and Tic-tac-toe Examples 7m
- Introduction Intuition, K-means Algorithm 9m
- Using Unsupervised Learning to Map Art and Words 9m
About the authors
Katharine is a software developer, having worked on medical software, Big Data and complex event processing, web development and Machine Learning. She has given a number of international conference talks on her experiences in the software industry. With a background in science, law, mathematics and more recently studying for a Masters in Computer Science, she (unsurprisingly) loves learning!
James Weaver is a Java developer, author, and speaker with a passion for cloud-native applications, machine learning, and quantum computing. James has written books including Inside Java, Beginning J2EE, the Pro JavaFX series, and Java with Raspberry Pi. As an Pivotal Developer Advocate, James speaks internationally at software technology conferences.