I think the videos were bad for a number of reasons: - there was an odd amount of explanation of what neural networks are. you should assume by this point we know what a neural network is. - the videos were very bad at explaining concepts. I think longer videos that explain more clearly what the object are would serve this course well - the explanation of what an RNN in was awful. - i thought the explanation of embeddings layers was awful. - in the word2vec lab, the visualization in the plane in the lab doesn't match up with your explanation underneath at all. - you hardly explain the mathematics behind everything (fine, this is not a math class) but then blow through the coding implementation. please choose one or the other and explain more. To reiterate, I think these topics are far too subtle to compress into 2 minute video, and you should provide references for further reading. This was far and away the worst of the AI engineering stream.

This is an extremely un-educational course and a hugely frustrating experience. It is fundamentally a voice going through whatever appears on a series of slide stacks just like a robot would. There is no effort to make you understand anything and no actual time to do it while you hear the voice running through the text. The only practical way to acquire the knowledge contained in the slides is to stop every 30 seconds, read, look up somewhere else (google, forums...) to actually consolidate the knowledge, and then click the play button again. I am a proficient and quick learner and have a good background on neural networks and gen-ai use and programming and I was completely incapable of following the explanations given in this course after the first 5 minutes: boring, robotic, ineffectual, and very counter-productive. This has been a very frustrating experience from a learner's perspective and my advice would be to take this course out and rethink it from scratch, as it certainly does not serve its purpose at all. I left one star because the knowledge is actually there in the slides. The information is contained in the slides, it is simply never actually conveyed to the audience by the reading robotic entity in charge.

the lab code is buggy. You face issues with almost every cell. Some core concepts on which entire module relies itself are outdated or are deprecated. For eg torchtext was deprecated in 2023. What is the point of teaching it in 2024. Extremely disappointed with IBM...

Very clear introduction of the NLP with hands-on exercises

Short and precise course with good explanation.

it's a great course with awesome subjects.

excellent course

Great Course

Documentation is often one of the weak points of IBM´s courses. Great content, but documentation is not friendly-printable or is missed [slides!]. On the other hand, I´m thankful for allowing us to download of the course videos.

3* because of the videos and materials. if it would be only about labs it would be 4*. Video materials could be much more than slides and AI generated speech. Even with prior theoretical knowledge, videos were confusing to me. It seemed like there were some explanations missing, or glue between the slides and subtopics. And this was especially present in the Module 2. I strongly suggest to either go through deep learning and/or NLP courses by deeplearning.ai or to try to find their or someone else's videos on YouTube. In that context, course could have been complemented with more materials for theoretical concepts. IBM courses so far are lacking good theoretical base and explanations. Labs were good and can be even better if for module 2 connection between encoder and decoder was visually better explained (e.g. more gifs).