This intermediate-level course introduces the mathematical foundations to derive Principal Component Analysis (PCA), a fundamental dimensionality reduction technique. We'll cover some basic statistics of data sets, such as mean values and variances, we'll compute distances and angles between vectors using inner products and derive orthogonal projections of data onto lower-dimensional subspaces. Using all these tools, we'll then derive PCA as a method that minimizes the average squared reconstruction error between data points and their reconstruction.
Imperial College London is a world top ten university with an international reputation for excellence in science, engineering, medicine and business. located in the heart of London. Imperial is a multidisciplinary space for education, research, translation and commercialisation, harnessing science and innovation to tackle global challenges.
- 5 stars
- 4 stars
- 3 stars
- 2 stars
- 1 star
来自MATHEMATICS FOR MACHINE LEARNING: PCA的热门评论
This is one hell of an inspiring course that demystified the difficult concepts and math behind PCA. Excellent instructors in imparting the these knowledge with easy-to-understand illustrations.
Great capstone for the three-class Mathematics for Machine Learning series. Assignments were way harder and programming debugging skills had to be appropiate in order to finish the class.
This course was definitely a bit more complex, not so much in assignments but in the core concepts handled, than the others in the specialisation. Overall, it was fun to do this course!
Challenging, but doable. Has some bugs in coding assignments, but clearing them out makes you understand things better. Get ready to spend extra time understanding the concepts.
This course is well worth the time. I have a better understanding of one of the most foundational and biologically plausible machine learning algorithms used today! Love it.
Programming assignment for week 1 wastes to much time due to lack of instructions.\n\nThe notebook also does not work...(maybe locally , but I have other things to do).
Course content tackles a difficult topic well. Only flaw is that programming assignments are poorly designed in some places and are quite difficult to pick up at times.
This course demystifies the Principal Components Analysis through practical implementation. It gives me solid foundations for learning further data science techniques.
Teaching pacing is good, and clear in explanation. It will be good if there are some examples about how we should apply all these theories to some real problems.
I found this course really excellent. Very clear explanations with very hepful illustrations.\n\nI was looking for course on PCA, thank you for this one
I learned a lot in this course, though the last week was somehow hurried and the lecturer didn't spend enough time to piece the whole stuff together.
Solid conceptual explanations of PCA make this course stand out. The thorough review of this content is a must for any serious data researcher.
Course addresses important subject, but I worth like to have more in-depth explanation of the mathematics by the instructors and more examples.
Felt like explanations in this course were a bit confusing, but otherwise, it was a very interesting course. Thank you so much for doing this.
Excellent course. The fourth week material is the hardest for folks not comfortable with linear algebra and vectorization in numpy and scipy.
What a great opportunity this course offers to learn from the best in this simplified manner. Thank you Coursera and Imperial College London!
This was a very hard course for me. But I think the instructor has done the best possible he can with presenting and explaining the course
The final Notebook contains some errors (Xbar instead of X, passed as an argument). Otherwise a very well organized course. Thanks a lot!
Highly informative course! Loved the depth of the material. Found this course content highly useful in my current project based on PCA.
Coding assignment is hard for people who are not familiar with numpy. Would appreciate some material at least going over the basis.
关于 数学在机器学习领域的应用 专项课程