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 Satyam s•
Simple and understanding
by Otavio D Z B•
Missed graded assigments
by JackT T•
Nice fundamental course
by Ashwini. A•
i like this courses
by Luigi S•
Nice and clear
by LANKE N B J•
by Abdur R•
by Rohit K S•
by Ashwani Y•
by Muhammad A•
by Egi R T•
by Zayn K•
by Wellington B R•
by RAJAT S•
by Milad M•
by M n n•
by Amit K•
by Pablo A•
After taking courses 1&2 of this Specialization I had high expectations for this course on NLP. I am a linguist learning ML so I was really hoping to learn a lot. However, this course has no graded assignments, which was a disappointment as I really enjoy the challenge that those present. Making the assignments not required really takes away from the experience imo. Additionally, the content seems kind of basic in this course. I feel like the first 3 weeks are spent doing mostly the same thing. It isn't until week 4 when we finally get to something somewhat interesting. I really wish this course was better structured. I will be checking out other NLP courses, but this one was a bit of a disappointment.
by Jesus E R•
Very, very basic course. It over-explains the simple things but glosses over important concepts and choices (choice of optimizers, choices of some layers, among others).
Additionally, the course is overly repetitive. Videos explain the same thing over and over. I understand this is more about Python and Tensorflow than is about ML but even then, we spend longer time explaining the non-TF parts of the code than on the TF parts and the reasoning behind them.
This course also lacks practice. Quizzes focus on the exact syntax for a function but not that much on the whys. It lacks programming exercises (first week has a very simple workbook that doesn't teach much).
by Aditya L•
This course has a lot of exciting material. However, it can be challenging and hard to work on if you are not comfortable with RNNs and LSTMs already. It cross-references to many videos of Andrew Ng, which would be ok, but when you see those videos you realize you need to learn more things and so on. Additionally, the assignment is ungraded which takes away some of the challenges. Definitely a good introduction but to get deeper meaning on this you have to do your own research and studies on the material quite a bit.
by Albert Z•
Not that bad, but should cover more details. For example, the num_words parameter in Tokenizer is actually len(word_index)+1, but the tutor does not mention that in the lecture. It troubles me a lot in the assignment until I finally figure that out by myself. I still recommend this course If you want to take the tensorflow certificate exam. But you need to learn more by yourself. You'd better read all the API documents for the commands mentioned in this course to make sure that you understand them correctly.
Some lessons in this course were so repetitive that it seemed like a waste of time. Week 2, in particular, felt monotonous and really put a damper on my interest in the information. Despite there being some useful code to learn, Laurence talks though the code in video clips, and then does a screencast of himself talking through the same code in a workbook. I have really enjoyed the 2 courses prior to the NLP course in the TensorFlow in Practice Specialization, but this one seems less developed.
by Asgeir S•
The course material is good.
However, multiple URLs are outdated both in the course material and in coding exercises (which makes some coding exercises not working).
Optimally some of the coding exercises should be updated to newer versions of TensorFlow (some things from the 2.alpha version are no longer available in version 2.4.x and some things are deprecated).
Also, it would be great if the coding exercises were graded (like for earlier courses in this specialization).
by Kevin H•
The content is good, the videos well paced. The code examples are also very useful.
But I feel the structure of the class is too loose. In my opinion, it would benefit from having assignments that must be submitted and graded.
Maybe they could be small and focused - like focusing on just working with the tokenizer, or setting up Embedding layers or LSTM layers. There could also be one where you load a pretrained model and writing the next token prediction loop.
by Ethan V•
I'm a bit disappointed with this specialization overall. I think I expected a deeper familiarity with tensorflow, more exposure to the TFData abstraction for large datasets, more low-level exposure to extending your models to fit a specific problem in your domain. Instead I feel like this specialiaztion would better be titled "Black box manipulation of the Keras API". That's a shame, given how solid the first deeplearning.ai specialization was.