Excellent. Isn't Laurence just great! Fantastically deep knowledge, easy learning style, very practical presentation. And funny! A pure joy, highly relevant and extremely useful of course. Thank you!
Great course for anyone interested in NLP! This course focuses on practical learning instead of overburdening students with theory. Would recommend this to every NLP beginner/enthusiast out there!!
By Hannan S•
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 :)
By Christian L•
Great course with fun examples! Probably more valuable after completing Deep Learning Specialization/Sequence Models by Andrew Ng (https://www.coursera.org/learn/nlp-sequence-models)
By Sinha, S•
This course covers the overview of NLP without going into much mathematical detail. In short time span, many things can be learnt from this course, helpful for the beginners.
By Mostafa G•
Excellent course to take after completing Deep Learning Specialization
By Yuanzhe L•
Great course as always
By Juan C B R•
By Serhii K•
The course is really nice, especially if you just start working with TensorFlow.
But I think it could be better to have 1 week for all course, with 8-10 min videos, instead of splitting it into 4 Weeks with 1-2 min videos
By Alice M•
More graded coding excercises would be useful, the way it was done in the first specialization course. The optional coding exercises have a lot of code that wasn't covered in clarity within the videos.
By Juan E C P•
I think that it should have included some graded excersises, just like the ones in the second course. I really enjoyed this one, but I felt it could be a little more practical.
By Mikhail C•
Not as strong as the previous 2 courses in the specialization. Each step building on itself (embedding --> LSTM --> stacked LSTMs) did not really show much improvement in the actual exercise. Also the main pieces that impacted accuracy and loss the (buffer size and batch size using SHUFFLE and BATCH_SIZE) were completely ignored. I also wish there were graded exercises that forced me to learn both the data ingestion, tokenization, and training pieces. I struggled through those in course 1 & 2 but it paid off in my understanding. Data preparation wasn't covered as in depth as the computer vision course either (i.e. how do I deal with large data? can I flow them in like the image generator?). Lots of broken links as well (some people might not know to go find the github repo to get the optional exercises).
Concise explanations and nice demos leading into a very easily digested lessons. Covering every important fundamental aspects without being bloated by too much technicalities (which are only useful in a more advanced implementation). But again, basic is still basic. The quizzes def need more work as to not rely on a simplistic memorization problems (which almost doesn't exist on always-connected working environment) and instead should ask for actual concepts or understanding.
Def not deep enough if you pay for it, but a good one if you can finish it during the trial period.
By Aditya G•
The Course was good. The content was the introduction of Natural Language Processing and it does well in explaining the theory and all but I think they should have dived a bit deeper into the topic. Sometimes in between the course, it does feel that much exciting, because some part of the code showed does not have any proper explanation. Maybe I'm saying these things because I'm in sync with Andrew Sir's teaching earlier. But overall this course will be best for beginner and it should be a great start for moving into the NLP field.
The pros: An abundance of Python Notebooks that help to build intuition, fascinating datasets, and some interesting NLP applications.
The cons: This course feels like content in progress compared to every other course I've done so far. The material is too general and references other courses when it should use this opportunity to reinforce content from other courses, e.g.courses in the DL Specialization. The lack of required coding exercises, together with the reuse of quiz questions in Week 4, were a disappointment.
By Luiz C•
As previous Courses of this Specialization, this Course is very suited to teach you the main concepts quickly. But it lacks the hands-on practice required to go into the implementation details. At the end, you won't have the minimum experience to usefully apply the learned concepts
By Alexander M•
The Course gives some nice code snippets one can reuse, but it just forms a starting point. In General the Course does go into any depth and I would recommend it only to beginners.
By Cassandra d C•
A little bit too simple/easy. Not as much practice required as the other courses in the specialisation.
By Udit G•
The evaluation process is very simple and based on memory rather than on concepts. Overall, courses in this specialization do not motivate the student to learn. The Andrew Ng's courses are much more detailed in theory and evaluation. These courses stand nowhere them.
By Stephen H•
Echoing what others have said. The course information is largely links to official documentation and videos from other courses. The notebooks are cookie cutter follow alongs. There really is little content here.
By Ian D•
This is a *very* surface level course. You might learn the mechanics of using tensorflow to perform some operations, but the moment something goes wrong you'll have no idea why.
By Naeem M•
This whole specialization was not even close to the quality I expected after taking Andrew's Deep Learning specialization. This one was especially bad because it didn't even have graded programming exercises, unlike the two first courses. By the end, I was just fast-forwarding the videos and solving the quizzes with almost no mental effort. Basically, if you have taken Andrew's courses, you don't need this one and you probably will be better off just doing free tutorials for Tensorflow and Keras.
By Orko G•
Some of the things in the exercises are incorrect and the exercises aren't graded. Quiz for week 4 was essentially the same as the Quiz for week 3. This course didn't have enough material to be considered a full course. Most of the topics were rushed through without giving enough background, with external links for details and even practice tutorials.
By Plabon D•
Very Very disappointed. "Shallow" is the word comes into my mind when I think about the lectures of this course. Materials are top-notch, but not enough attention were given into the details. Felt like it was made in a hurry. Why would someone pay a good amount of bucks to take a course like this that can be finished within a single day ?
By Mahmoud K•
Quality of this course is not good compared to previous two courses. It is super percised and many things are not well-explained or explained very briefly! The second course was better structured and valueable. I was hoping that this one is as well, because I am very interested in NLP than Image Processing.
By Jan G•
Programming exercises are badly described, very often it is not obvious what then expect from you. Also some of them are broken, are correct answer is wrong and you are expected to reproduce the wrong answer (week 1).
By Ivan A•
Giving feed back so it may trigger some evaluation on this course. The course is very weak. Lacks material and engagement feeling. I would say increase the aterial 800-1000 percent , add homeworks, etc..