Mar 09, 2019
Good intro course, but google colab assignments need to be improved. And submitting a jupyter notebook was much more easier, why would I want to login to my google account to be a part of this course?
Aug 14, 2019
Great course to get started with building Convolutional Neural Networks in Keras for building Image Classifiers. This is probably the best way to get beginners into Deep Learning for Computer Vision.
创建者 Muthiah A•
Jan 06, 2020
Useful start for practitioner.
创建者 Rushikesh W•
Jan 04, 2020
Good practice for coding on tf
创建者 Ivan N•
May 19, 2019
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.
创建者 Alon L•
Mar 19, 2019
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)
创建者 Philip D•
Apr 06, 2019
Decent enough but much too abbreviated and lacking the depth I expected from a deeplearning.ai course after taking their deep learning specialization.
创建者 Stavros K G•
Mar 10, 2019
I know that it is an introduction but I would like more staff .
创建者 Antonio S•
Sep 17, 2019
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).
创建者 Dragos B•
Mar 15, 2020
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
创建者 Aladdin P•
Aug 04, 2020
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.
Jun 20, 2020
No deep details for functions used
创建者 Walter H L P•
Aug 06, 2019
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.
创建者 Mahdi S•
Nov 09, 2019
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.
创建者 Siddhanth D•
Oct 13, 2019
What a crap professor. Really wish Andrew Ng taught this course instead. I have no clue what this teacher is talking about he makes 2-3 min videos of complicated material and blabbers about it while referring us to online videos and other resources instead of just explaining it.
创建者 Stephen F•
Jun 07, 2019
I mistakenly bought this course , Note 43 euro is for this one simple module, be aware please!!
创建者 Ahmad F•
May 06, 2020
If you're starting out as a beginner AI practitioner, this is a very good introductory course. The prerequisites for going through the classes are really low. You just have to know basic python and the basic mechanics of deep neural networks beforehand. After completing this course, you'll be very proficient at modelling neural networks to classify images with very high accuracy using tensorflow keras.
This course also explains briefly how to import data of your choice to your neural network to train on, which I think is very cool. It also teaches you about convolutional neural networks, which is what the top industry experts use to do their AI jobs. The exercises in this course are well made, they help you really understand the concepts by making you code them by yourself. All in all, this is a very good introductory course, and Andy Morone is an amazing teacher.
创建者 Frank Z•
Jul 15, 2020
This course is very friendly to beginners starting to get to know TensorFlow. The only skill needed is basic Python programming. Another good point for this course is students don't have to obtain a local machine that could run the TensorFlow. The tasks could be done over Google Co-lab, which is very conveniently friendly. The only shortcut for this course would be the source codes provided are based on TensorFlow 1.X. Right now, the TensorFlow has released 2.X. Since tf V2 has taken out some functions in V1 as well as changes some expression, it would be very inconvenient if you wanna download the code and test or do your work on your local machine.
Overall, this is a course that I would highly recommend as a beginner.
创建者 Edgar C O•
Jun 23, 2020
As an introductory course to the Tensorflow platform I think it is excellent. As it is mentioned in the title this is not a course where you are going to see in depth what it is behind the algorithms or the theory behind the implementation but it provides extra links to other sources where the interested student can read on their own, which I think is good. It is self-contained, the material in the course it is well explained and the ideas about how to use the platform and the ideas of how to solve the problems are well-defined. The exercises are defined in such way that the student can immediately used what he/she learned from previous materials. It is a great introduction to Tensorflow.
创建者 Jeremy V K•
Jun 24, 2020
Amazing class! As an absolute beginner, I wanted to learn machine learning and AI but didn't even known where to start. I even started a different machine learning course which I could not follow well, and expected similar results with this class. But this class, this class is aimed at beginners, no need for any pre-requisite knowledge and the google colab environment ensures that it doesn't matter what hardware you currently have, since its all done in the cloud. Also the practice notebooks are very detailed about each sections of the program. I'm not a master at machine learning, but atleast after this course I feel that I too can learn it.
创建者 Dhamotharan B•
Jun 29, 2020
I have used Tensorflow in my projects but never know some of the tricks which could improve the model.I was very dependent on transfer learning. But, now after getting to know much about Tensorflow, I feel so confident . A basic understanding of how model works with Tensorflow is essential and Laurence Monorey provides you some of those basic tricks and concepts of how neural networks works with Tensorflow. I can assure anyone here taking this course would definitely give a try to adjust the way they have approached towards implementing Tensorflow in their projects. Thanks Andrew and Coursera for bring up this initiative.
创建者 Prashant S•
May 21, 2020
I found this course very helpful because of working example at every step. First there is step by step explanation of each line of code after which you can play around with the code by making small modifications to it and observing results. It is not heavy on math behind machine learning but there are certainly lot of new terms. Most of time i googled those term to learn a bit more about those. Overall, instructor explanation is extremely good and easy to follow up. Its extremely important to play around with the code samples. All i needed was a browser and no installation on my laptop to finish this course.
创建者 Michael B•
Jul 31, 2019
I love the courses put out by deeplearning.ai. I previously took the 5 course deep learning sequence taught by Andrew Ng (which I would also recommend), and am VERY pleased with the first course of this sequence taught by Laurence Moroney.
The lectures are broken into small, digestible chunks. The quizzes are hit core knowledge points w/o any tedious "can you do this by hand" nonsense you see in some other courses. The notebooks provided in the course offer useful templates for adapting to other problems. Just amazingly well done in every aspect.
Looking forward to taking the rest of the sequence!
创建者 Prafull P•
Nov 09, 2019
This course is an excellent starter for people who want to learn about Tensorflow and how to use it to create neural network model very quickly . The Instructor explains every thing in very lucid language.Course is well organized to help you go from beginner to an intermediate quickly. Great articles and videos links will also come your way so even that would help you improve and enhance your knowledge. Highly recommended for someone who wants to learn about Tensorflow and enter into the field of ML & AI. A Big Thanks to deeplearning.ai for creating such course :)
创建者 Kirt U•
Jul 22, 2020
The course material and presentation is excellent. However some of the course tools are complete trash (code autograder in particular - this is because the code that was shipped off to the code autograder wasn't the code I had been working on - it wasn't until later that I realized that the tools were taking predefined [expected] file names and not the code I was working on - this is only year 8 of this otherwise excellent project - 8 years and the tools are still substandard). Also the quizzes are too easy.
创建者 Hannan S•
Oct 28, 2019
First of all, the course was amazing! I found it great for the following reasons:
- Laurence Moroney (Instructor) was very professional and clear while delivering the knowledge
- The introductions by Andrew NG were really nice
- Easy to understand codes and understanding of thr underlying principles
- Varied topics such as CNN, NLP & Time Series
- Very insightful by providing expert opinions about different ways of model optimization
I really enjoyed the course and I thank the instructor for the same :)
创建者 Curtis P•
Jul 27, 2020
Coursera and of course the instructors have really got this online teaching down to a science allowing students to cover often quite complex topics in an easy to digest and efficient manner. Even though it does skim the surface it does give a very good 10,000 foot view of the objectives and capabilities of the topic and technologies. To get same perspective on my own would be a lot of googling, trial and error, without the benefit of knowing 100% that I was covering the appropriate knowledge.