It would be grate that the examples have been updated to the TF 2.0 version.

i loved it. I have an undertsanding of different deep learning models

Was a really fun course, but the final assignments were very lengthy.

Good material but almost all the labs are too slow to run properly

Good introduction to Deep Learning Models with Tensorflow

Very informative, could use some more room for practice.

Lab content must be updated with latest TensorFlow.

Thank you. thought it's could be more deeper

no audio in the last learning unit 5.

some questions are a bit confusing

Met expectations

It is ok

good

This course had some distinctly terrible aspects, for instance, introducing a topic without any form of background. Ie. "Transformers: here's a transformer". Before moving on to other subjects. It's optimized for time, and not for learning or subject matter. At times, it seems cobbled together from other courses. The producers couldn't be bothered to properly format, use proper style, or even at times make code examples properly functional in both the the slides and labs. Was this course created by professional software engineers? The course has no rigor - it does not prevent you from skimming through and simply completing each module. You may pass this course by doing no work whatsoever. It is entirely up to you what you get out of this course. That said - if you do complete the course by watching each video twice, taking notes, and doing external projects outside of the class, you can actually learn something.

This is a pretty good course on the different types of neural networks and their cousins. The presentation slides are really well done. The examples are programmed in TensorFlow. But the course does not really teach very much about TensorFlow itself. The opening lecture on TF describes it in terms that suggest this was created for TF 1.x, rather than the new structure in 2.x. But that turns out not to be an issue since they go into little detail on TF itself.

The programming examples are really good. However, most of the time, the CognitiveCourse.ai web site on which they run is usually not working. So you often cannot use the labs in conjunction with the lectures. You have to go back and access the labs sometime when the website is working.

While the lab and videos explained the concepts really well, the codes from the labs are outdated. They are using tensorflow version 1, while tensorflow version 2 (current version) is very different. I have to go outside of this course to learn the new codes.

Other than that, every other aspect of the course is good. explanations are clear, videos and diagrams are very detail. Just the right amount of labs etc

The course is good in order to gain an understanding of the different types of Neural Networks, Algoritms etc. are present and what their purposes are. However, the course stems from 2019 and doesn't seem to be updated that much if at all. The mechanisms and coding required have change significantly since them, so the actual exercises are kind of outdated.

Lots of code and theory heavy, which is not a bad thing, but there is little thought given over to the actual learning objectives. There is also no real opportunity to practice learning to use TensorFlow. There are likely better tutorials out there, which is a shame because a lot of effort has gone into this course.

Overall the content is good, it's just such a pity the labs are sloppily, and not well put together. I found many mistakes going through them all. Some are easy 'copy-paste' errors, others are more fundamental. I think the authors need to do a full review of the labs and update them as required.

The Course was more about the the types of neural networks and how they work than Tensorflow, except for week 1 where we had a Tensorflow introduction, I could gather a lot from the programming assignments but I think there needs to be more about the Tensorflow library in the lectures.

I found the practice notebooks of this course to be lacking due to two reasons: 1) The notebook links are broken, resulting in my not being able to complete them. 2) The notebooks do not have practice sections where we could code ourselves following the examples given.

Pretty good content overall but the course does not actually teach you how to build deep learning models; it is lacking useful homework/programming assignments, provides extremely basic overview of the ML theory and simply walks you through a few worked examples.

Nice review when you have previous knowledge. The PyTorch course was more detailed. Nowadays, Pytorch is becoming more popular than TensorFlow and the new Keras API supports it (PyTorch) as well.

I think it is time for IBM to update its syllabus.

Good basic understand. No mix ups between general understanding and coding. Much better explanations than in the other courses of this specialization. Unfortunately content is still too shallow.

The course is good, but 1) the lab environment is not working at all.... I had to run the notebooks on google colab ! 2) The code is outdated. Tensorflow 2.x is out.