This course introduces the products and solutions to solve NLP problems on Google Cloud. Additionally, it explores the processes, techniques, and tools to develop an NLP project with neural networks by using Vertex AI and TensorFlow.
- Recognize the NLP products and the solutions on Google Cloud. - Create an end-to-end NLP workflow by using AutoML with Vertex AI. - Build different NLP models including DNN, RNN, LSTM, and GRU by using TensorFlow. - Recognize advanced NLP models such as encoder-decoder, attention mechanism, transformers, and BERT. - Understand transfer learning and apply pre-trained models to solve NLP problems. Prerequisites: Basic SQL, familiarity with Python and TensorFlow
AF
Lot's of good information. I cannot wait to start using this knowledge. Thank you!
ZS
Awesome course, Great tutors they teach tough topics very easily like RNN(LSTM, GRU), Encode Decoder and attention.
MD
Very good.The explanation of the RNN was very good but the tensor2tensor was very hard.
PR
Great way to practically learn a lot of stuff. Sometimes, a lot of it starts to go over head. But, it is completely worth the learning curve! Definitely recommend it!
SA
This course explains basics and advance concepts from NLP with simple language. Course is nice but more mcqs and exercises are required.
MN
Very helpful but needs more in depth detail how attention works, how encoder/decoder trains and makes predictions
BS
Good Course with enough practical exercises to get some hands on experience.
VS
E​xcellt course. Covers overviews of important topics and provided links for further deep readinf
ND
I have only one remark, please improve lesson regarding NLP by includin model build etc. Otherwise course is excellent and was helpful for me
HS
Though not focused on fundamental concepts, it's a great course to learn to use tensorflow and google cloud platform for sequence modelling.
JK
Very helpful course to understand NLP and how to use GCP platform at basic level.
HK
Very informative, very much useful to my ongoing work on NLP.
Showing: 20 of 75
Several exercices do not work as described, with error messages.
Explanations of what we are doing are light.
Too focused on GCP. Could be more on DL itself.
Videos were too short. Explanations of the key concepts were really poor. Quiz in week 1 had error that was raised by the user 6 months ago and it is still not fixed. Coding section had library mismatch that led to errors. The presentation of the materials were good.
Maybe this course was too advanced for me. I did the other course on tf and that felt too easy. This was unreasonably hard. There was no explanations at all before labs and there were like 5 labs a week. how are we supposed to do them? i skipped nlp entirely, because i could not follow it at all due to zero guidance and explanations. The only skill i got from this course was to copy code from internet, but i could do it before
One star, but not to content. But because the course don't have "Audit" option. It's mean that after subscription ended and you received certificate, You can't more access to video material in course. When subscription active, You can use mobile application and download video material for studying offline. Before yours subscription ended, copy video material to safe place for later review.
p.s.
But the course content deserves a higher mark - 4-5 stars. As others courses in this specialization
Excellent course for those who know RNN. Knowledge is refreshed and techniques are consolidated. More details about Google ecosystem is introduced.
This was a very interesting course on NLP and Time Series. My only concern is that some notebooks worked for python 2 mode and not for python 3. Also, the tensor 2 tensor lab could not be completed in 2 hours, as some of the training may take more than 3 hours to complete.
Overall, good information, great technology and great teachers.
Thank you.
Subscribing to this course only gives you option to run assignments on Qwik labs, and they're very poor for these kinds of assignments. You won't get any feedback on assignments anyway since there is no grader.
If you want to check out the material it's better to just clone training-data-analyst from github and do these assignments on GCP free tier.
No Doubt COURSERA is always best AND MNC like IBM,Google courses associated with coursera are MIND-BLOWING.
The Instructors are so great at Explanation Part that hardly anyone won't Understand All the Topics
I would love to thank all the INSTRUCTORS who created such a Awesome Content for us.
My Personal Ratings For All the Instructors: 100 / 100
The lack of synchronization between the videos and labs is extreme in this course, but the lectures are excellent and the subject area covered is very broad.
I have only one remark, please improve lesson regarding NLP by includin model build etc.
Otherwise course is excellent and was helpful for me
Tutorial content frequently doesn't match that described in the videos.
Some introduction to machine learning concepts but often pushes you to a Google automated version of it rather than describing the principles in much detail.
Issues with tutorial content being incorrect has been flagged for a long time - comments in the forum go back many months, but nothing has been done to correct it. Videos also reference content not present in the course, feels a bit cobbled together from other courses. One package taught is now also described as deprecated on its page Appreciate software moves quickly but considering it is a Google package you'd hope they'd keep up to date on that.
I enjoyed the introduction to a range of topics in the area especially RNNs and encoder-decoder but the issues with the labs significantly detract from the merits of the course.
Why dont you make a easy lab works ? I mean the procedure is too much. As simple like Andrew Ng's course would be great.
Amazing course, I also took a bunch of other Deep-learning and specially Sequence Modelling courses from other renown instructors and institutions. However, this is so far the best. better than all of them.
1- Very well structured
2- Fairly advanced in contents and techniques
3- Reasonably challenging.
4- Full free access for a trial period ( not all courses offer that)
5- Access to GCP for free
Amazing course, well done Google
Excellent Sequence Models explanations and examples to learn from, I quite enjoyed all the fantastic tips and best practices recommended by Google, looking forward to the next course in the specialization.
Great way to practically learn a lot of stuff. Sometimes, a lot of it starts to go over head. But, it is completely worth the learning curve! Definitely recommend it!
I like it because it is very relevant to my work. The dialogflow part is a bit weak. I am not sure if it is the product or the course.
Awesome course, Great tutors they teach tough topics very easily like RNN(LSTM, GRU), Encode Decoder and attention.
This course is short and sweet, and covers many helpful usecases of GCP tools related to the course topic.
Everything was fine except the solution videos are old, that why you should update with update code.