Sep 8, 2014

Learn Machine Learning Using These Online Courses

Share:

In 2011, Stanford professor Andrew Ng launched his first MOOC, teaching just over 100,000 students about machine learning. Ng has said that the course, which turned out to be very popular, led to the start of Coursera. Today, Coursera reaches 7.5 millions of users around the world, and Ng’s Machine Learning course continues to receive wildly positive reviews from seasoned and newly initiated programmers alike.

Programmers are using machine learning to build really, really smart algorithms — and thanks to educators like Andrew Ng, people are starting to take notice. If you want to begin your education in machine learning and explore some of its applications, check out our round-up of some of the best MOOCs on machine learning today.

Beginner Machine Learning:

1. Machine Learning (Stanford): This highly-rated Stanford course is perhaps the best introduction to machine learning. Users praise Professor Andrew Ng for his ability to expertly explain the mathematical concepts involved in different areas of machine learning.

Level: Beginner | Duration: 10 weeks | Start date: On now | Read reviews

2. Learning From Data: This introductory course from CalTech dives into machine learning as if telling a story: Can machines learn? How exactly?  Students will gain an understanding of the theory behind machine learning, and gain experience with different algorithms and models.

Level: Beginner | Duration: 10 weeks | Start date: September 25, 2014

3. Principles of Autonomy and Decision Making: Gain an overview of the different ways systems make decisions: from logic to heuristics to model-based reasoning.

Level: Beginner | Duration: Self-paced | Start date: Always on

 

Intermediate Machine Learning:

4. Machine Learning (University of Washington): This interactive course goes beyond basic concepts to explore neural networks, learning theory and vector machines — among other things. It is taught through “supervised learning” — meaning that the correct answers is usually given to the student during class.

Level: Intermediate | Duration: N/A | Start date: TBA

5. Practical Machine Learning: Part of John Hopkins’ specialization in Data Science, this course focuses on learning the components and applications of prediction functions.

Level: Intermediate | Duration: 4 weeks | Start date: July 07, 2014

6. Introduction to Convex Optimization: This high-level course will help students recognize and tackle convex optimization problems. The course will also go over applications in areas like finance, computational geometry, mechanical engineering and more.

Level: Intermediate | Duration: Self-paced | Start date: Always on

 

Advanced Machine Learning:

7. Machine Learning (MIT): This graduate level course from MIT approaches machine learning through the lens of statistical inference.

Level: Advanced | Duration: Self-paced | Start date: Always on

8. Prediction: Machine Learning and Statistics: Another graduate level course from MIT, but this one explores machine learning through predictive models and “the study of generalization” from data.

Level: Advanced | Duration: Self-paced | Start date: Always on

9. Topics in Statistics: Statistical Learning Theory: This course provides an in-depth analysis of the theories behind statistical learning, and covers empirical process theory, Vapnik-Chervonenkis Theory and more.

Level: Advanced | Duration: Self-paced | Start date: Always on

 

Introduction to Neural Networks:

10. Neural Networks for Machine Learning: This course introduces users to algorithms that are “inspired by the way the human brain works.” These algorithms are used to build machines with things like speech recognition, image retrieval, and personalized recommendations for users.

Level: Intermediate | Duration: 8 weeks | Start date: TBD

11. Introduction to Neural Networks (Spring 2005):  This course delves deeper into the topic of neural computing and learning, and covers models of perception, motor control, memory and more.

Level: Advanced | Duration: Self-paced | Start date: Always on
Introduction to Genetic Programming:

12. Bioinformatic Algorithms (Part I): In this University of California at San Diego course, students will deal with real genetic data to learn more about the computational methods used in modern biology and genome sequencing.

Level: Intermediate | Duration: 10 weeks| Start date: Sept 15, 2015

13. Bioinformatics Algorithms (Part II): If you liked the first one, continue your studies with the second half of UCSD’s course in modern computational biology.

Level: Intermediate | Duration: 10 weeks| Start date: Jan 15, 2015

 

Additional Resources:

Interested in learning more about machine learning? Read up on what Andrew Ng is doing at Baidu, or check out Kaggle, the company that wants to make data science competitions a thing.

And for those of you interested in building a career in data science, check out our Learning Path at Springboard to get started!