PCA & multivariate signal processing, applied to neural data (Udemy.com)

Superb! - this excellent course delivers fascinating and highly relevant content in a complex, cutting-‎edge field. It's advanced, intellectually stimulating, and presented professionally with clear ‎structure. Mike excels at explaining sophisticated concepts like PCA and GED within the context of ‎neuroscience applications, making challenging material both accessible and engaging. Highly ‎recommended for anyone interested in neuroscience or computational modeling in brain research.‎

High quality contents, Mike puts lots of effort into the realization of his courses and you can see it (he also answers to your questions rather quickly in the Q&A section). I strongly suggest to do this course if you already have some Linear Algebra foundations (e.g. knowledge of dot product, matrix multiplication, matrix rank, matrix inverse, eigendecomposition). If you are not confident with Linear Algebra he has another great course on Udemy (also strongly recommended) and this can be a perfect segue. In this course he will teach you the basic mechanisms underlying some of the most relevant dimensionality reduction and source separation methods from different perspectives: from math to code. I personally gained a lot from this course and I will definitely incorporate this acquired knowledge into my own research.

I am not a Neuroscientist but a Mechanical Engineer. Yet over 90% of the course-content is relevant to what I do and helps me to improve my data-analyses skills. It is presented in a way that allows good understanding of the complex material. The teacher presents it in a way that makes it look simple, but the attention he payed to course details (speech, graphs, sheets, color, programming, assignments, support, to name a few ...) makes the course enjoyable AND educational. He is an exceptionally good teacher and so it this course! Take it! You'll enjoy it!

Excellent course! Mike X Cohen is a wonderful professor and he is very present. He tends to respond rather quickly with well thought out responses, and you can tell he clearly is excited about the material. Generalized Eigendecomposition was the crescendo of this course and I enjoyed the build up to it. This course gave me the tools to understand many scientific articles I was reading and having trouble with dealing with EEG classification as well as work on my projects and have a foundational basis on which to experiment with different preprocessing and modeling techniques and pipelines. I would recommend this course to anyone trying to understand Eigendecomposition as it relates to Signal Processing. I'm super excited to finish the other Mike X Cohen courses dealing with Signal Processing and am grateful to have someone teaching these concepts in an orderly clear and stepwise fashion.

My opinion is not based only on this course but on all the other courses that I attended. Mike is really doing a great job of simplifying the concepts, great examples, and hands-on experience with MATLAB exercises. As a neuroscientist, I benefited a lot from taking his courses. I learned valuable information as a scientist and learned how to simplify specific signal processing concepts for other students. Thank you, Mike, really great job! I am glad to recommend this course to other students.

The course is organized, and dives in some elements quite well. Yet I would have expected a slightly deeper analysis and mathematical development for ICA methods. The course only aboards the JADE approach and not even mention FastICA.

The course is wonderfully explained and the teacher has a thorough knowledge of the matter. Just to say something I miss little bit, it is that I'd preferred to have not only Matlab source code, but also some math/theory notes (even limited, perhaps just the slides) on the topic of discussion. And a plus it would be notes on recommended bibliography, any references for further study (books if any, apart from scientific papers).

To enhance my understanding from sensor space to source space inspired me to opt for this course. After making this course halfway, I can simply say "WOW". The reason for this "WOW" is that I learn more than what I expected. The importance of PCA and GED, It's real look and visualization in the source separation impressed me. I hope to learn more in the next half of this course. Great job by Dr. Mike, I am really thankful for his contribution to making these scientific/mathematical terms/concepts/procedures visible for the early career researcher like me.

Prof. Mike X Cohen courses are the best coursed available online. The way he explained the concept, not only about neuro science but also math behind it is amazing. The code he provide is so neat and clean that any one can easily replicate it. I do work in python instead of matlab. The way he teach intuition about each step is so compelling that i convert the most of matlab code to python, though i am a beginner. I would request him to create more course, taking a case study and include machine learning chapter in it. One suggesstion i would like to give him, please increase font size of matlab code, as i find difficult to read it .

About the instructor: He did a great job, he definitely has extensive experience in teaching so you can learn very effectively from the course. What I *really* appreciated was that he answers all the questions and he provides very useful answers to those questions: He tries to understand where the confusion lies and explains it to you. Maybe I was just lucky but I actually get an answer back from him within an hour at the weekend. About the course: The entire course is very well organized, each individual lesson is well-structured. Each lesson starts with an introduction about the current learning goals, how to approach the problem and the he uses a bunch of different visualization techniques to explain you the topic. If you are a neuroscientist, you will have enough knowledge, skills, code and theoretical understanding by the end of the course to start with your own data analysis. Having a psychology background is also fine, although I took his linear algebra course before this one.