Learner Reviews & Feedback for Structuring Machine Learning Projects by DeepLearning.AI

This is a 2-week follow-up on the previous two courses in this specialization.

While it's a decent course that goes over a few interesting topics, I have a hard time giving it more than three stars. Reasons for that are below:

(1) Especially the first week felt very slow and repetitive. Most of the material could have been summarized a much smaller timeframe.

(2) The course went over some interesting topics in a very high-level way, but skipped a lot of the details that would have been very interesting to people looking to learn deep learning in depth (like the target audience of this course!).

(3) While I think the approach of having some themed case studies for the test is neat, a lot of the answers left me thinking "well, the correct answer would also depend on X which isn't specified". Good concept to test knowledge in a "discussion/oral exam" session, but IMHO bad for hard "wrong or right" multiple choice tests.

(4) Some videos had "black screen" times at the end, errors, cut-offs and repetitions were not cut out, and overall I think this had the least amount of "polishing" of the courses in this specialization so far.

I'd have preferred if the content of this course were a bit more steamlined and merged it into the other courses of this specialization.

Overall, I think that it was a good course but in my opinion, the knowledge of this course cannot be easily transferred to people with very few experience in Machine Learning. Therefore, I was wondering whether it should be the 3rd course or the 5th course in this Deep Learning Specialization! Moreover, in order for someone to deeply comprehend these concepts such that he/she is able to apply them in a Machine Learning project, he/she should work on a project on his own where he/she will meet these concepts and will have to search in order to solve them.Last, personally, even though I am quite satisfied from the courses, I would expect that one more course is added to Coursera which is going to require to build a Deep Learning project! I think that this course should be of more advanced level and require (not Intermediate as those ones) and should require from students to build projects like the ones builded in the cs230 class from Stanford.Greetings from a PhD USC student

The content in this course is excellent; however, the learning activities are insufficient for truly internalizing the material and do not follow evidence-based guidelines for learning (see the book, Make it Stick). The video lectures cover a lot of ground, but I found that many were a bit too long, often dwelling on points well after they were made. The problem is that the only actual learning activity is a 15 question multiple choice at the end of each week (and there are only two weeks of material). The course would really benefit from having questions embedded in the videos, similar to Udacity style courses. Following those with the 15 question "simulator" would then reinforce the material. However, this course also needs programming assignments at the end of each week so that students can actually gain real experience with the methods and suggestions.

Good general information is provided but this material could be layered into the other courses in this specialization. I would recommend that the case studies be based on real industry problems that present the backstory of the decisions the teams made. Also programming assignments would be useful in which the impact of incorrectly classified training data is studied in detail or in which images that have been synthesized are used versus not used. It did not take too much time to work through this course so the information provided is worth the cost, but I am not convinced that this series is viewed as more than an opportunity to make some money off of the name brand. Much of the information provided so far is covered in the Deep Learning - Goodfellow text and the extras are vague and repetitive.

There's some very good tips in this course, but it's not enough content to even warrant the two weeks that's it's spread out over. It would have been high quality material as a part of another course or as an addendum, but it hardly stands alone by itself. Unfortunately, that seems to be the trend on Coursera to provide sparse content spread out over multiple courses to milk money. Entire specializations could be fit in one course but now it's 7. Viewed in context of this specialization, a lot of what Andrew Ng lectures on seems to be padding to lengthen the videos since he tends to repeat the same points over and over and over. In other words, a lot of what Andrew Ng lectures on seems to be padding to lengthen the videos ... see what I did there? Maybe I can get a job at Coursera?

Some interesting information in week 2 where multitask learning, transfer learning and end-to-end vs sequential nets are discussed. The bit on breaking down your errors into classes will also come in handy!

Week 1 was quite repetitive and seemed to be mostly common sense, probably could have cut these videos in half without losing much. Personally I watched most of this at 1.5x speed to avoid falling asleep. First quiz also had some less then conclusive answers - there's a lot of disagreement in the forums! Some issues also with the cutting of the videos, those these are only a minor nuisance overall.

Overall, less impressive then the other courses but still useful knowledge can be obtained here.

From a philosophical standpoint, I especially liked the 2 interviews in this course.

A huge decline comparing to the absolutely amazing precedents. Though the content is important and relevant, it is designed mainly for actual practitioners in the field, which is a mismatch with the audience of the specialization. The lecture is repetitive to the extent that I doubt I hit backwards by mistake. The video is raw with vocal tests and black-frames uncut, minutes of vacant content. The quizzes are trivial and not enough to really solidify your understanding comparing to the perfect programming assignments before. If out of the context of the whole series, I would give it 1 star. The quality of the specialization is great, but to pack such little content into a "course" is disappointing.

This course offers some good advice when it comes to (much needed) practical considerations when training neural networks, and to a reasonable extent machine learning algorithms in general. I personally don't see myself successfully applying the content on Multitask Learning, Transfer Learning and End-to-End ML in real scenarios straight after finishing this course unless I go ahead and learn these in more depth. The "flight simulator" approach to applying what has been taught was great! I would have liked more (perhaps optional) exercises in this format. I would have also not minded a longer course that could go more in depth into the bias-variance tradeoff and the aforementioned topics.

This course is too high level and short - while the content and concepts themselves as presented were invaluable, they were insufficient to give a good overview of what a basic machine learning project structure needs to contain.

It would be much more helpful if programming exercises were provided which give an indication of *good code architecture* when it comes to structuring a machine learning project. How do we write reusable functions/classes which split, process, and combine train/dev/test data, feed them into a learning algorithm, and carry out the necessary error analysis?

Great materials but 1) quiz questions are sometimes vaguely stated thus causes confusion, while almost no one from the course stuff is giving satisfying answers in the forum to help clarify; 2) multiple mistakes in video editing, e.g. part of clips played repeatedly, and blank dark background without any content somehow got inserted into the video; 3) really hope to see another programming assignment in Tensorflow; not that I don't agree with pilot-training assignment, but programming would be good to have because essentially this is where data science projects are built.

Not exactly what the title promises. In this course you will learn more about the overall approach of a ML than how to organize your data and best practices on comunicating and sharing information. (at least in week one, so far haven't started week 2).

Now I've done week 2, is much better than week 1, but still the problems presented are way more in a way of the rational behind the ML projects than Structuring the project itself, peharps a better title would be: "DEFINING GOOD MACHINE LEARNING STRATEGY APPROACHES" or something like it.

I like the project perspective on ML tasks and the content a lot. I have two critics though:

1.) I am missing at least some smaller steps into the direction of implementing certain concepts (e.g. changing a model for transfer learning purposes)

2.) In addition, the videos are quite long, sometimes it seems as if the same audio/video sequence was added to one video multiple times.

Anyways, many thanks for this course. I think with some minor improvements it will reach the level of the other courses which are simply great. Many thanks!

Whereas the 2 courses that preceded this one in the specialization are focused on explaining how Deep Neural Networks work, this course is more for people with experience of NNs and how to troubleshoot issues that might occur in the wild.

I think the content here is really great, but if you're someone like me with no real world experience of Deep Learning, it is not so interesting as the other courses which explain the core concepts of the approach, rather than how to fine tune a real system to get better performance.

The curse is quite simple, there are a few interesting insights so it's not all bad. I feel I've learnt some interesting ideas. However, I feel it's quite incomplete. There are several problems that happen "in the wild" that are not covered. There is more that image classification and speech recognition to machine learning, therefore the experience of Andrew makes the course content biased to problems that are interesting but very specific. I was expecting something better given the quality of the first ML course.

While it was useful to see some of the best practices in ML, and the course contains practical information, the information could be delivered more concisely. Also, we get a lot of intuition, but the delivering of the material is getting less and less rigorous. The very least it would be nice to see some sources attached to each video. 3 stars may be a bit harsh, and it does not mean that I do not think it is important to listen to this course, it is more about the way of delivering the information.

As always Dr. Andrew Ng offers great insights into specifics of hot topics (Multi-Task & Transfer Learning) as well as providing unique "studies" as quizzes to complete each week. These quizzes are the primary take-away from the 2 weeks that offer a lot of redundant lecture material. Save some time... just make the 'simulations' the focus of the class then... perhaps use some transfer learning toward a different application in the quiz.

This is a decent course, but I found it less useful than other courses so far. There seemed like a lot of redundancy and repetitiveness in the descriptions, and I think all of the information could easily be fit into a single week that more concisely captures the exact same information. The quizzes in this course were interesting because it had a very applied nature (trying to capture real world scenarios you may encounter)

This is a valuable but misplaced course. After the first two courses, I expected to get hands-on experience with TF+Keras, and after that, or beside it, learn about strategies of tackling ML projects. However, by first talking about the strategies, one could miss many valuable points because one is not deeply aware of the necessity of these points. Hence, the course was boring comparing the last two.

Good class, but I think as part of the Deep Learning specialization that it'd be more useful if there were some programming exercises to reinforce what is taught in the videos.

Week 1 seems to reference a "flight simulation" programming assignment, but then it just has a description and a "mark as completed" button. Maybe this programming assignment is still being worked on or the content is wrong.

I'm grading this course lower than I graded the two previous ones for two reasons: 1) while there are many examples given in the course, it is actually hard to take a step back and see how to concretely achieve some goals in a more generic manner, and 2) in the assignments (which are made of quizzes), many "wrong" answers would actually be appropriate if more context was given.

This course really felt a lot more thrown together than the other ones, with a less cohesive lesson and quizzes that had more subjective material in them than usual. And perhaps it is a bit nitpicky, but I found the swipe Ng took at computational linguists to be kinda distasteful. I know there is a lot of bad blood between ML and AI people, but it has no place in coursework.

Thanks Andrew for this course! However, it is obvious that less care was taken for the preparation of this course compared to previous courses (more typos, etc). Some of the sentences in the quiz were not clear at all and made it very confusing to choose from the options. A little programming assignment at least would be nice to reinforce our learning of the materials.

The course goes through valuable practices when it comes to analyzing errors, and Andrew does a great job at explaining. Though, I felt that there should have been programming assignments to accompany the theory. I strongly prefer the layout of previous courses, "quiz -> programming" as that feels more interactive than just doing a quiz in the end.

nice lectures and very useful knowledge learned by Andrew, but it is really short and no working assignment through real code.... and quite a lot more mistake than course1 and 2. Really love the two previous courses, don't work why the quality of the course drop off so sharply.

Somewhat disappointed, but still really great lectures.

It gave much more industry driven approaches to improving the model. I as a student don't have that much experience with deeplearning and that' why I couldn't relate with most of the topics that were going on here. Of course, the teaching quality was supreme. But the course's contents itself felt a little bit dry to me.