Coursera Free Course: Machine Learning
About Machine Learning Course
Machine Learning is the science of working without explicitly programming the computer. Over the past decade, machine learning has given us the opportunity to gain a much better understanding of self-driving cars, practical speech recognition, effective web search, and the human genome.
Machine learning is so widespread today that you probably use it dozens of times a day without realizing it. Many researchers also believe that this is the best way to advance human-level AI. In this class, you will learn about the most effective machine learning techniques, and gain practice in applying them and be able to work them out for yourself. More importantly,
You will not only learn about the theoretical foundations of learning, but also gain the practical knowledge needed to apply these techniques quickly and powerfully to new problems. Finally, you’ll learn about some of Silicon Valley’s best practices for innovation as it relates to machine learning and AI.
Machine Learning Coursera course provides a comprehensive introduction to machine learning, data mining and statistical pattern recognition.
Machine Learning included topics:
- Supervised education (parametric / non-parametric algorithm, support vector machine, kernel, neural network).
- Unsupervised education (clustering, reduction, recommendation system, deep learning).
- Best practice of machine learning (bias theory; machine Learning and innovation process in AI). The course will also draw from numerous case studies and applications, so that you will also learn how to apply learning algorithms in creating smart robots (concepts, controls), text comprehension (web search, anti-spam), computer vision, medical information technology. , Audio, database mining, and other areas.
Learner Career outcomes
Instructor
Andrew Ng, he is a top instructor in coursera online courses platform.
Machine Learning: Learner Reviews
1. Thank you very much for the excellent speech. I’m just thinking about the back propagation algorithm. When we count errors backwards, why do we use matrices theta instead of their opposite.
2. I really enjoy this course. I learned new exciting techniques. I think the main positive point of this course was its simple and understandable teaching method. Many thanks to Professor Andrew Ng.
3. Overall the course is great and the instructor is great. Machine learning is interesting and I now feel I have a good foundation. A few minor comments: Some projects had very helpful code where the student only had to fill in a portion of the algorithm. I would love to work through more code. Also, there were times when the slides did not have complete equations so it was difficult to put them together when writing code. Finally, I wish there was more coverage in vectorized solutions for algorithms.
