It's a great course! Very well structured, with an amazing amount of jupyter Notebooks (Colab) to work with, in a real hands on approach.

Just one criticism, which is why I didn't classify it as 5 Star: There isn't much of an evaluation. The tests are a bit easy, and it would be good to have at least one extensive assignment (maybe with other datasets...).

It's just that I feel the contents were really good. But if I can just pass the tests easily, I feel it doesn't really count as much of a "quality stamp" (to have passed this course).

Great course, however it was annoying having to "roll the dice" so to speak to get the answers right. Perhaps if it wasn't left to chance to achieve the right grades, it would of been much quicker and easier to get through. I'd say this is also a course for everyone who's had at least some experience in programming. Understanding some deep learning helps, but you definitely need knowledge of how to code in python. If you can code well in Python and are good with math, then this course would be a breeze for you!

Really helpful and easy to understand. I know several programming languages but not Python, so I appreciated the labs that helped me get up to speed with Python.

The only downside is that I am not particularly interested in image classification, which is the main focus of the course. It was interesting to learn about all the convolution techniques but I doubt I will use them in practice. It would have been nice to have examples of AI problems that were not image classifcation, like a regression problem.

Clear explanations and the tasks, which are easy to understand, make it a really enjoyable journey to learn the depts of Machine Learning. One problem I had was following:

The assignments at the end of each week require me to go to a web-lab, to which I unfortunately couldn't connect. There was always an error which lead to the problem, that I couldn't test the code I wrote there. Therefore I had to copy all data-sets on my own working-station und try it out there and hope, it would work on the lab.

Overall the course is nice and provided me with some skills. The main drawback is that the course does not demand large amount of student's input. If you are quite familiar with Python and have some basic ML understanding, I guess you can do it in less than 48 hours (including videos, readings and assessments). The tests can be guessed, the coding exercises are better, but also largely rely on the codes provided during the course. Having in mind this was "introduction", 4 stars.

Very quick and simple introduction to Neural Network using Keras's Tensorflow high-level API. Simple understandable introductory examples about how to build a neural network or Convolutional Neural Network in a few lines of code. There's no Math in this course. The downside is you won't understand how it works under the hood, and why it works (or doesn't ;-)). If you want a deeper understanding, you must study "DeepLearning Specialization" and/or "Machine Learning" course.

A great starter course. My only suggestions:

In the code completion exercises, a note or two indicating what is expected to be done, would be helpful. You kind-of have to go back and look at the previous problems to guess what is being asked of the student.

A complete slide deck would be very helpful, if only to be able to write notes onto the slides. And it would allow the student to do less scribbling, and more pondering of the problems being discussed.

Nice class, covers some basics of tensorflow and learns how to quickly build a NN. Not too fond of the quizzes: a few unclear question/choices and lots of "learn by heart" questions (like: what is the size of the pictures in this specific dataset, what is that specific param name) which you can easily answer without understanding too much. The assignments are simple enough for an introduction, quite close to the lesson examples but still interesting.

This course is good, and is fast paced.Mr Mororney is an excellent instructor.

The course is real good and basically focuses on CNN and ANN. The only shortcoming was that they didn't really teach 'pure' tensorflow,this course is really about Keras and not tensorflow. We are taught how to use Keras with tensorflow as backend .

They should have taught basics of tensorflow such as place holders and what are tensors!.

Nevertheless, it's a good course.

This is a great introductory course which focuses on implementing basic Keras models. The only gripe I have with this course is the programming assignments. I experienced many, many issues while trying to submit the assignments even with proposed solutions from the discussion board. This isn't a show-stopper; just a little frustrating. Otherwise, I highly recommend this course to anyone getting started withTensorFlow & Keras model building.

I've been an machine learning engineer for 2 years, taking this course to push myself to learn new TF2 features. I don't think there's focus on the new distributed training feature in TF2, codes are still TF1.x.

I think the last quiz had some really unclear questions, could be improved.

Other than that, I love the hands-on practice part. Wish we explain more on why model performance is so brittle in the horse vs human classification example.

Although course content seems to be nice but a regular update with the current tensorflow version needs to be done. Also, In course content there are topics listed just to tell that in next section what you will study(even provided 10 mins for that) and that is a complete waste and poorly put in the content section-this needs to be fixed.

On a positive node, this course is very useful to start and I recommended this to beginners.

Great review of TF and the newer tf.keras API in addition to practical advice on deep learning projects. Lawerence has been a pretty good instructor, clear and to the point, with some good exercises. For beginners, though the course skims over some of the basics - although these are covered in Andrew Ng's Deep Learning specialization, which I took some years ago. All in all, a handy course to get cracking on TF and Keras again!

Brilliant Course for getting started with Tensorflow. The only thing I would like the instructor to include are explanation for non -TF stuff, like matplotlib codes. It would really help develop additional skills apart from making TF models. Going online to find the working of each command in a different library like matplotlib really broke my flow and my focus . So, that would be a welcome addition!

I really liked that it was very hands-on and made it very quick and easy to get up to speed on using TensorFlow for Machine Learning. That said, there was a lot less content that I expected (I finished the '4-week' course in about 1.5 days), and I was a bit disappointed that the focus was exclusively on image classification. A little variety in terms of the problems being solved would've been nice.

The course is targeted for an audience with a basic knowledge of the machine learning techniques. With that in mind, it delivers a comprehensive first look at the calibre of the TensorFlow framework. For the more advanced practitioners the programming exercises and the quiz might seem a bit on the easier side. Overall it is a great place to start for those who wish to begin with TensorFlow. Kudos!

The contents and instructor is excellent. Unfortunately one is faced with mainly two downfalls. Fist, there always seems to be some sort of submission problem which usually involves some kind of "hacking" from the user's part to make it work. Secondly, it's very hard to get answers to most doubts since the activity in the discussion Forums is very little, specially from instructor-level sources.

Overall a very good course (with knowledge from the deep learning specialization) to get a deeper knowledge in tensorflow. But sometimes in the exercises you feel a little left alone, because of missing information (example Week 4, which folder should you use, what's the resolution of the images, you can find out but that requiered (for me I had to downloaded the files and check what i needed).

Great course giving a very basic overview of some features of Tensor Flow. The assignments could be implemented a little bit better, there were a lot of version issues relating to tensor flow.

Also, the course would benefit from moderation of the discussion forums. Overall very happy with my experience however and would recommend for anyone looking to get started in machine learning.

The only reason I'm not giving it 5 stars is because I think some concepts could be explained in more details, such as batch_size and number of filters. Maybe that will be covered in the next courses in this specialization, and if that turns out to be the case, I'll change the rating to 5 stars. Generally, excellent teachers and able to explain complex topics in a simple manner.

The course is quite light even for introductory one. At the same time, I enjoyed examples of NN implementations in colab and elaboration on how the code works. The most interesting for me personaly were hints and techics helping to develop a better understending on how the NN are builing its knowlarge on input data. I look forward to checking other courses of specialization out.

Excellent content with comprehensive explanation for each line of code, but the submission process is really suffering. (Long submission time and numerous unknown errors, but they can be solved by solutions provided by the student forum ) In the Jupyter notebook, there are some syntax errors (like inconsistent namings) which require manual fixes, needs more improvement.

That course was superb, but there were much references to other content, ik that was important but just as a suggestion I would say you can put this specialization in 5 courses or add 1 Week in each but please teach that all, by the way 4 stars were just to grab your attention as review otherwise I literally loved the content thank you Mr. Laurence and Mr, Andrew

Should probably spend more time on lectures. They're a little too short, and almost exclusively just designed to discuss snippets of code that help you solve the immediate assignment. I realize that this is a hands-on course, but intuition provided could have been much better. If you want to know how that's done, refer to 3Blue1Brown's series on Neural Networks!

very structured from the beginning, the time required to complete this course is calculated very carefully so even if you're a beginner with deep learning you'll be complete the course on time. there are a lot of useful resource links as well which reduces the learning effort. i really liked this course and it made me more confident to pursue the specialization.