via Machine Learning.

In this course, you’ll learn about some of the most widely used and successful machine learning techniques. You’ll have the opportunity to implement these algorithms yourself, and gain practice with them. You will also learn some of practical hands-on tricks and techniques (rarely discussed in textbooks) that help get learning algorithms to work well. This is an “applied” machine learning class, and we emphasize the intuitions and know-how needed to get learning algorithms to work in practice, rather than the mathematical derivations.

Familiarity with programming, basic linear algebra (matrices, vectors, matrix-vector multiplication), and basic probability (random variables, basic properties of probability) is assumed. Basic calculus (derivatives and partial derivatives) would be helpful and would give you additional intuitions about the algorithms, but isn’t required to fully complete this course.

The Great Works of Software — The Message — Medium.

I realized that each one of these technologies set out to help people do something but consequently grew and changed over time. Each ultimately provided a way for large groups of people to talk about and think about very difficult problems:

  • Microsoft Office: How do we communicate about work
  • Photoshop: How do we create and manipulate images?
  • Pac-Man: How do we play?
  • Unix: How do we connect abstractions together to solve problems?
  • Emacs: How do we write programs that control computers?

Computer people often talk about products. But each of these five have come to represent something else—an engagement with hard problems that are typically thought to be in the domain of philosophy, literature, or art, rather than programming. This software doesn’t just let people do things; it gives them a way to talk about and share what they did.