Learner Reviews & Feedback for Introduction to TensorFlow for Artificial Intelligence, Machine Learning, and Deep Learning by DeepLearning.AI

More or less the course takes on Tensorflow's implementation of Keras rather than Tensorflow native env. It also only focuses on computer vision domain. Kind of misleading course title.

Learn a lot of tensorflow basics, which is good. However, the course is very short and easy to complete, and I cannot apply the neural network learned in this course to actual work

Ce cours balaye les fonctions de bases de la librairie d'abstraction Keras et permet de construire rapidement des réseaux de neurones complexes.

When each layer visualization was taught, I didnt get that part nor in the program. Else its a great starter course

It's relatively simple course if you've already finished Andrew Ng's deep learning specialization

Great introductory course to learn the application of TensorFlow with Keras.

Great course, but can be completed shortly instead of many weeks session

Amazing way of putting all the stuff together

Useful start for practitioner.

Good practice for coding on tf

The course is ok-ish, as are all the other courses in the specialization. This review is for all the courses in the specialization. I have a general shallow overview of DL but wanted to learn about TensorFlow and about Keras. For this it provides a good overview. You could learn it from tutorials too but at least I benefit from taking a course, as it motivates me to finish. But, the material is very shallow and it is a shame that there are close to no graded exercises. The quizzes are super easy. And there is no capstone project. If I didn't know the basics before I probably wouldn't have understood anything. If you know a bit of DL beforehand you can easily take one course per day. The fact that earning the certificates unfortunately degrades the value of it. If you finish in a month (and therefore only pay for a month) I think it is worth the price, even if what you learn is not that deep.

I get that this is a separate course from Ng's deep learning course, but I found the lack of theory (or even recommendations of best practices) disturbing. Additionally, I thought the videos were way too short and would have appreciated it if they had gone into detail into each Keras method used, the parameters for it, etc. For example, on the last assignment we were supposed to use a callback on accuracy to end training, but nowhere in the videos did it mention how fit_generator() handles callbacks as opposed to how they were handled with fit().

Lastly, and most importantly, this course was advertised to be a course on Tensorflow. However, this is not the case. This is a course on Keras; Tensorflow's API. If you came here looking for how to implement a DL algorithm from scratch in TF, this is not the course for you (or me apparently).

I think this is a great way to introduce NN to people that have never seen one.

But there was very little depth in this course. I finished the 4 weeks in an afternoon. The external references were at times way too advanced, while the exercise code was way too simple. That being said, the Jupyter notebooks were a great material and helped me start with NN really quickly. The MNIST dataset is brilliant and hank you for showing how to do it.

The reason why I gave 3 stars is because the MOOCs aI have done in the past were much more extensive and gave plenty of theoretical background. Some people might think that the lack of theory lowers the entry bar for students, but in my book that's a tutorial not a course.

Save yourself the $40 price tag and buy a book on the topic, there are plenty out there.

Material is very well explained and very relevant but the course is short in comparison to other deeplearning.ai courses before and could be richer both in content and in exercises (which are also not graded)

Decent enough but much too abbreviated and lacking the depth I expected from a deeplearning.ai course after taking their deep learning specialization.

I know that it is an introduction but I would like more staff .

I am quite disappointed with this course. First, it should not been called "Introduction to TensorFlow" but "Introduction to Keras", which is a TensorFlows' (TF) API that entails a higher layer of abstraction. Basic data structures, estimators, graphs, etc. are not explained through the course. Second, video lessons are too superficial and lack of content. They remind me to those of the Machine Learning Crash Course from Google. That is, as an opener/introduction for Deep Learning (DL) are fine but they are far from being an essential training tool in DL (unlike the Deep Learning Specialization here in Coursera). Finally, content is too basic. This course requires an intermediate level, so students are supposed to be already familiar with basic DL concepts. I understand that this first course within the specialization is an introduction, but I just begun the next course (Convolutional Neural Networks in TF) and it is more of the same. Laurence is still working on the binary classification problem and only at the end he treats the multi-class problem. Instead, I was expecting to implement CNN models like ResNets, Inception networks, and applications like object detection or face recognition in TF (not in Keras). For me, it is not worth spending time and money for what you learn in this course. The good part is that, because videos are short and exercise are easy, you can finish the whole course in just one week (or less if you are 100% working on it).

Maybe I had unrealistic expectations following the original 5 courses from deeplearning.ai. I understand the target audience and need for simplification, BUT there are multiple outright wrong statements, that are unacceptable (will list below):

1 `Softmax takes a set of values, and effectively picks the biggest one, so, for example, if the output of the last layer looks like [0.1, 0.1, 0.05, 0.1, 9.5, 0.1, 0.05, 0.05, 0.05], it saves you from fishing through it looking for the biggest value, and turns it into [0,0,0,0,1,0,0,0,0] -- The goal is to save a lot of coding!` - no it doesn't do that, it takes n numbers and gives n numbers which sum to one and respect all original inequalities. and no it doesn't save time, you still need an argmax.

2 in the first course there's a linear regression trying to learn f(x)=2x-1. The course says you can't get it exactly because you don't have enough data. Of course you have enough data, 2 points are enough to describe a line, and that regression has a closed form solution. SGD with fixed LR is the only problem.

3. Immediately after, also first lesson, it says that sometimes loss goes up and that's called overfitting.

Those were just a few...really I understand it doing baby steps for developers without maths background, but I'm not sure this is doing them any favors..I've also showed these to a bunch of my colleagues and we were on the same page about it

I am not very satisfied with the course. It does feel quite professionally made, but there is no depth. It feels as if the teachers of the course had some difficulty when deciding on the prerequisites. I think it would have been clearer if the course would just have said: take this course after the deep learning specialization because this will build on knowledge from previous courses. Then, focus ONLY on teaching the coding part, explain what is TF, what is Keras, in DEPTH. For example, all the quizzes are more theorethical questions: these should be ALL code in TensorFlow. E.g, what is the following code doing? I guess it's just the first course, so depth is not expected but what I've read so far, it wont change in the following courses. I'm dissapointed and Andrew you should set a higher standard for your courses. Hope you will take lessons and not let this happen in future courses, I wasted my money and time on this.

No deep details for functions used

This series of courses is just a 'Hello World' introduction of Tensorflow/Keras. The instructor just touches the surface of some code from the Tensorflow document without explaining some really fundamental concepts (e.g. tensors). The videos are usually 1-2 min long, really a headache to watch. The quiz is too simple and poorly designed-- instead of thinking or calculating you just need to remember some basic concepts/grammar rules. Programming exercises are not really useful and there is too much duplicate work. Not worth the money if you plan to pay for it-- auditing is enough. I am disappointed by deeplearning.ai for producing such a shallow course.

Code and exercises look like they were made in a hurry, with a lot of errors that have not been addressed yet, even after been reported about 3 months ago. No challenging practical exercise (just need to copy the code from the previous notebook that the instructor supplied) (maybe making the function print "Reached X% accuracy so cancelling training!" was necessary to fool the grader). Weak theoretical test. I had high expectations, and now I am disappointed with this deeplearning.ai course. I do not recommend, TensorFlow guide have better material to learn about it.

I don't actually get the purpose of this course: teaching deep learning or teaching deep learning with TF? Can there be anything else? If the former is the aim, one needs to learn how a deep learning algorithm works and why it is successful. If the goal is teaching TF for people who are familiar with deep learning, first the structure and logic behind TF and then the coding parts should be taught line by line with details.

This course, in my point of vies, has nothing to present.

This is was the worst course I have ever taken on Coursera and my sample size for courses is statistically significant. a) The grader is not good. b) The infrastructure was not good. c) To complete the course I have to copy the code to Google colab, run there and then copy-paste the code back. This course was very very basic and from an industrial standpoint, it was way below expectation.

Far far too easy. As a big fan of the deeplearning specialisation I was very disappointed in this course. I don't know what they think the learner is supposed to come away with from this course. If this was all the course a person took they really wouldn't know very much at all