Learner Reviews & Feedback for Computational Neuroscience by University of Washington

This course was enjoyable, to say the least. It helped explained the thinking behind the conceptualization of existing algorithms that I've been introduced to in other courses for AI, but it further explained how they were mathematically derived.

Muy instructivo y entretenido! Felicitaciones a los autores del mismo.

I really enjoyed this course and think that there was a good variety of material that allowed people of many different backgrounds to take at least one thing away from this.

As a beginning PhD student in computational neuroscience, I found this course to be incredibly useful as a refresher. And as an introduction to the subject, it is incredibly engaging, interesting and, of course, one fun adventure! Many thanks to both Rajesh and Adrienne for this course!

Made it really easy for me to get into this field. So very inspired.

It was an amazing journey!

Excellent Course! Very in-depth and informative! Exceptional faculty and extensive supplementary material as well!

Intreginity of strategy of learning from stractch

A very nice introduction to Computational Neuroscience world. The main course advantage is the matching between theory and practice (programming).

Very enjoyable course!

I learned a great amount from this course. Now, I want to learn more about neural coding

Perfect course. The only feedback I would give is, if possible, to include slides in the weekly material for review instead of just text. Thank you for this amazing tour through Computational Neuroscience!

Starts off great but get rushed 3/4ths into the course. Too much content, too little explanation, but recovers swiftly to end on a high.

Recommended

Pretty good. A bit of mathematical ambiguity and lax notational conventions, but the course content was solid and presented clearly.

As a self-paced student, I like this kind of course. I hope to see a whole specialization in this field with final capstone project. Thanks.

The course over all was very good but I didnt given it five because of the following : in course 2-5 the lectures were not coherent and the there was no expalantion for how certain experiments or measurments were done and hence natural progression to associate the mathematics. The lecturer tends to speak fast and sometimes eat her words so there was absence of clarity . The lectures were not well structured . on the otherhand lectures 6-8 were much clearer in presenation and scope and more linked with the quizes.

A good look at mathematical models focusing mainly at the synapse and neuron level. The math came a little fast and furious for my 30+ years antique math training.

I'm a professor in psychiatry with a background in clinical psychology. I conduct clinical research to understand the neural mechanisms involved in psychiatric diseases. I found the course very informative and covers topics in computational neuroscience that are critical to further my research in the computational direction.

The course involves a moderate amount of math, which is absolutely necessary to understand the materials. For someone like me who did calculus more than 20 years ago (i.e., rusty), I often found the explanation of the math too fast. I had to pause the videos multiple times to digest the formulas and re-watch some videos to get a true understanding of the materials in order to complete the quizzes successfully (especially in later weeks as the concepts get more advanced). The supplementary tutorials by Rich Pang are extremely helpful. He talks at a slower pace, allowing time for you to think along the way. He is also very good at helping you to get an intuitive understanding of the complex concepts. I would recommend watching Rich's tutorials before watching the lecture videos. That way, you would understand the lectures more readily.

The quizzes are overall well designed and helpful in terms of facilitating the consolidation of your understanding of the concepts and methods covered in that particular week. I don't know if it's just me. I tended to spend a lot more time than the estimated time (e.g., 3 hours instead of 1 hour) to complete and pass a quiz (especially later ones that involve more Matlab programming).

Overall, I found this course very useful and overall well constructed.

Learnt concepts about Neural Networks, Supervised / Unsupervised / Reinforcement Learning. Covers topics about Information Theory, Statistic and Probability. Matlab / Python assignments.

I have really liked this course,but there is a lot of statistics I didn't expect to find at the beginning. Ihave given me exactly the flavor of what Computational Neuroscience is and what are the field of applications, which are REALLY interesting. Honestly I have found a bit too condensed the part regarding the description of "cause" and all the related statistic stuff which I think should deserve some 1 or 2 videos with solved problems. All summed up, I think this course is really worth of taking. Best regards to the professors and to the mentors and to those who have given me a lot of help with their posting on the forum. Their doubts and the relative answers have really been enlightening for driving me towards a better understanding of the matter. Thank you to all of you.

This course serves as a nice introduction to the field of computational neuroscience. However, at some points, more than basic knowledge of differential equations and probability & statistics is needed.

I found this course helpful and inspiring for my research activity. I suggest it to anyone who has basic mathematical skills.

Great course, if a little bit outdated today.

Many of the lectures do not make a plenty of sense relative to their quizzes. The lectures are rather theoretical and the quizzes are rather practical. Also, one of the professors have better didactics than the other. Either way, it was quite an adventure (my hat almost didn't survive).

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