Kursteilnehmer-Bewertung und -Feedback für Computational Neuroscience von University of Washington

Overall - A good introductory course. But the last week, reinforcement learning and neural networks, could have involved programming questions.

I enjoyed the course very much and hopefully learned quite a bit about how to model neurons and some interesting new ways to look at methods like perceptrons and PCA. The course videos are short by very dense. Make sure you make enough notes and prepare enough time for all of them.

Great overview of a really cool field, gives nice intuitions for ideas in computational neuroscience.

I loved the course and the way Professors Rajesh and Adrienne conducted it. I only think the slides and lecture notes could have some more material. I'm a Software Engineer, with a background in Computer Science, but I have been far from math for quite some time (that's why I'm now doing a Cauculus 1 course). I got lost a few times in the quizzes due to lack of information.

But I loved the course and all the new knowledge I acquired. I will certainly recommend. it.

Good introduction to the topic. Course quite easy for engineers, may be quite challenging fro non-engineers. I didn't like quizes - they were too easy and were not provoking too much creative thinking. They were also easier than the lecture material.

Great course introducing fundamental concepts in computational neuroscience. People with weak mathematical background can master it although from time to time some more clarification could be helpful. Thanks so much for providing this :-)

interesting instructor and interesting content. Now I know more about the theoretical research related to neuro function and its connection to machine learning now.

Extremely interesting subject, many ideas and methods presented. Basic disadvantage is a method of source which is closer to seminar rather than leacture. But, lost of details is acceptable due to a huge amount of material. Advanced mathematics from various areas is necessary to fully understand all the ideas. Anyway, I recommend the course.

This course provides you with a brief introduction to computational neural science. You can benefit from it as long as you have basis in calculus and linear algebra. But for those who want to get the best from it, you need to build up your mathematics.

In general very good, but some concepts are rushed over due to the short length of the course.

Great course and really helpful for me.

Very good teaching skills by both professors and interesting guest lectures and tutorials. Assignements that demand your full attention. I would like some more depth as far as the developement of programming skills and the practice. Great intuition and explanation.

This is a very interesting course that provides many interesting ideas. At the same time it is quite challenging. Solid background in probability theory, linear algebra and signal processing is needed. Considering it "Introductory" level is misleading.

Quite interesting. I would see more explanation of some phenomena, though.

I liked the course. I enjoyed solving the problems and I am now confident in learning more advanced concepts and getting my hands dirty in neural networks and machine learning.

I only have one complaint like suggestion, if only the TAs or the instructors could show some examples of solutions or algorithms for the concepts, it would have been much easier. Although, i have understood the concepts, I have not yet grasped the implementations of the concepts in actual codes and programs. Please update the course regarding that. Thanks a lot again to Rajesh, Adrienne and Richard.

Being a high school student with zero background in computer programming, i find this course a bit hard.

In my opinion, the course level ought to be intermediate, not beginner. You can take more out of the course if you already have knowledge in this, or related, areas.

Interesting but too complicated for beginners

I love the information that has been given there. The problem I have with the course (and it's a big one) is that you start each lecture with great detail and then go to what exactly you want to achieve. Because of this it was easiest for me to understand when I watched all the videos each week and then went backward to get it.

I highly recommend "start with why" videos and book by Simon Sinek, it might give you some info on how to make the lectures more comprehensive.

Having said this - the merit is great and I love having the knowledge. It is just that it isn't well laid out.

[3.5 stars] The course provides an overview of some interesting topics. I would have prefer more emphasis on applications, perhaps in the form of additional exercises. Overall, I have my adventure hat on and I am excited to push on further into the neuro-jungle.

I just started the course. But it is exciting for me as a Machine learning and deep learning practitioner!!!

After week 1, the learning curve is steep. The topics are exciting but lectures are not engaging.

The professors who teach the course are very engaging and are able to make a challenging topic into something interesting and entertaining. The course is very math and programming-heavy, so make sure to brush up on these concepts and be prepared to know how to conceptualize neuronal behavior with mathematical equations and programming functions and vice versa. If you have any questions to post on the Discussion Forum, be prepared to look for the answer outside of the course - the response times of the mentors or other students are horrendous and there are even some instances where questions are never answered. This, as a biology person who had little to no experience in programming or advanced calculus, was the most frustrating aspect of the course. In regards to computational neuroscience as a course, the material itself is beginner-level, but the math/programming is definitely not (more like intermediate/advanced).

Nice content. Opens the gate of CNS for me.

But some explanations are just too virtual to be understood easily.

At last few weeks, the course talks about the relationship between NS and ML, which is astonishing.