Learn how machine learning algorithms work. Explore a variety of algorithms and learn how to set a structure that guides you through picking the best one for the problem at hand.
- [Derek] Have you ever wondered how with the push of one button, Uber can efficiently pair you with another rider and a driver that optimizes for price, pickup point, drop off point, and traffic? Or how Amazon can recommend to you that one item that you didn't even realize you desperately needed until it just popped up on your screen as a personalized recommendation? If you answered yes to either of those questions, then this is the perfect course for you. Hi, I'm Derek Jedamski. I'm a data scientist with a passion for machine learning. I'd like to welcome you to Applied Machine Learning: Algorithms. The amount of data generated my machines and humans is mind boggling. On average, we create 2.5 quintillion bytes of data every single day. To put that in perspective, that's 2.5 million terabytes or 2.5 billion gigabytes. In other words, we create a ton of data. Imagine all the power that exists in that data if we could just harness it and use it in the right way. Companies are tapping into the power of this data in different ways. They're doing things like speech recognition, image processing, recommendation systems, and even self-driving cars. They understand how to leverage the power of that data and use the appropriate algorithms to deliver powerful solutions. If you've taken Applied Machine Learning: Foundations, or maybe you've done some of your own exploration, you'll understand how to start tapping into the power of that data but you may not have a feel for the right algorithm to use for each job. As such, you might be leaving some real value on the table. By the end of this course, you'll not only understand how to attack machine learning problems in a pragmatic, thorough way, you'll also understand the various algorithms out there that you could use, you'll understand how they work, what drives them, and even when you should use them. Once you have finished this course, you'll have the tools to harness unstructured data of all types to go from that messy data to concise and accurate predictions from a machine learning model to deliver powerful solutions to complex business problems. Let's get started.
- Models vs. algorithms
- Cleaning continuous and categorical variables
- Tuning hyperparameters
- Pros and cons of logistic regression
- Fitting a support vector machines model
- When to consider using a multilayer perceptron model
- Using the random forest algorithm
- Fitting a basic boosting model