This course is incomplete, and is NOT recommended.

It uses Tensorflow 1, which is outdated now - should be updated to use Tensorflow 2.

It does not provide practice sessions.

Week 5 - Autoencoder - have no audio, no captions, nothing.

There is no final exam to ensure our competence. No labs we need to be graded on.

This is not a worthy Coursera course. It needs to be withdrawn and updated.

The codes need to be updated for TensorFlow 2.0.

course needed to be updated for labs. Now Google moved to Tensorflow 2.0 this year.

Mostly trivial quiz questions and no graded practical work. The certificate is therefore not worth very much.

There are 2 main problems with this course:

1 All the codes are for tensorflow version 1 and not 2 which essentially makes them outdated since the new version of tensorflow is quite different from the previous

2 All the explanations are very high level and will leave you with many questions. In short you cna learn as much if not more by watching any youtube videos on each of the topics

In general, the course seems to have been rushed out and the material is ridiculously slim. There is really no reason to take this course. You'll end up frustrated by the simplistic explanations and the fact that you are learning code which won't be relevant in a couple months.

Once again I am so surprised to see a reputable company such as IBM put their name on a product which is frankly embarrassingly bad. There is no way this course would be rated 5 starts by any human being which leads me to believe that they manipulate the scores with fake reviews.

The syllabus of this specialization is supposed to be rich; nevertheless, the lectures are not good at all. They mostly read the codes without diving into a proper explanation. The theory background is poor, and the labs don't teach you how to deal with real datasets, just random numbers, nor do they teach you how to implement an entire pipeline of code, just chunks of it without any scope (It seems to me). What could you supposedly expect from modules with lectures of 3 min - 8 min (tops)? I don't recommend this course if you don't have a strong NN background.

This course is a joke. It's a brief overview of a few types of models. Also there is no sound in half the videos.

Good content. A bit too fast on some complex concepts and missing audio for the last lecture but great lecturer.

Teaches more on Deep Learning models but less in TensorFlow

Lack of content, quizzes were poor, no sound or transcript on 2 videos. Took about 2 hours total.

needed more focus on coding and explanation of codes

Videos are good, but lack of graded coding practice is a big issue with this course. I barely knew how TensorFlow works before starting this course... and this hasn't changed after I finished with 100% grade.

I am not sure if no final assessment is a good idea. For the depth of the course it can possibly a major graduation killer but for practical reason you should put that back so people get to be serious with this course.

Deep Learning made me feel that there is a way to build models and classify data so easily and in a skillful way. Amazing course!

This is just introductory course, wish to see more content and in details concept. Too short introduction

It is very good to explain concept of Deep Learning by Example , it is so clear, and better understand

It helped me to understand how TensorFlow can be used to build the neural networks

A concise and comprehensive survey of deep learning models. Great labs (which sometimes don't run in IBM Skills Network. Thanks to IBM Watson Studio which came to the rescue in those cases). The labs reinforce concepts and illustrate Tensorflow coding to run the models. Lecturer is very clear and encouraging in tone. Thanks for the course.

Very clear explanation and well organized course. I give 4 stars because videos of Week 5 are missing the audio and subtitles.

Week 5 lecture video no audio

Lab is not update for tensorflow 2