The lectures covers lots of SOTA deep learning algorithms and the lectures are well-designed and easy to understand. The programming assignment is really good to enhance the understanding of lectures.
The course is very good and has taught me the all the important concepts required to build a sequence model. The assignments are also very neatly and precisely designed for the real world application.
By Guy M•
Great introduction to sequence models/RNNs. The real-world examples were very illuminating. Again, as with the previous course in the specialization, I felt some details of how to run/predict NNs using keras were lacking, which could leave a student floundering if they've never used keras before. This is in contrast to some other, much easier, tasks where hints were given.
By Alexander G•
Out of 5 courses offered I think this was the most exciting one as it combines everything learnt so far and teaches how to combine different NN modeling techniques to achieve desired classification/prediction features . For example, it is pretty much clear how one would go about building an app that would describe a picture to blind people and do that in many languages.
By Kévin S•
This short 3 weeks courses will make you work a little, exercice take at least twice the time write. You will learn about the famous LSTM, and how to use it on various tasks.
I'm not sure the 'translation' tasks is a good example but there is lot about it. Not a good example, because it is not state of art, and in the 'translation' business there place only for the best.
By Yogeshwar S•
This is a great course, and a great specialization. The professor explains the concepts across very well, not only in this course but in all courses of the specialization. My only gripe is with the notebook/hub/grading system which especially in this course has acted strange and cost a lot of time. That said I've learnt a lot, and am quite happy with the course content.
By SUJITH V•
Great course overall to learn the basics of sequence models and also get a brief understanding of the state of the art architectures used currently. The programming assignment on trigger word detection gives an insight into the practical machine learning implementation for speech recognition. This course combines both theory and practical advice in a very good fashion.
By Meynardo J•
Excellent course - and specialization! Andrew Ng's special talent is in being able to explain complex and difficult stuff with such clarity that you can actually understand it and follow. I found the exercises in this course tougher than in the previous four, but they were varied, useful, and FUN! Highly recommended to all who what to learn the "deep" in Deep Learning!
Because my research direction is NLP, so I think this course is very good for me. I learn how to implement the Sequence model such as machine translation 、Attention and so on. But the disadvantage is that there is no whole sequence model process. For me, The bigger problem is data processing and model. overall ,This course is good for me, I learned many from this.
By Ahmed R M A E•
It was a great specialization and a great course, thank you so much for giving me the opportunity to learn from you special thanks to Dr. Andrew Ng for his exemplary efforts and for teaching the greatest courses of the machine learning technology, I'm really proud of myself for finishing that specialization and I'm so grateful for all of you. Thank you ,Coursera.
By Matías P B O•
The whole specialization is excellent. I highly recommend doing it. The only minor comment that I add is that Andrew should include some links for further reading (along the courses for each topic or theme). I know that anyone can quickly look up for them in the Internet (and they can be outdated) but that would make the specialization even better in my opinion.
By José D•
This is Course 5 of the Deep Learning Specialization, and the last one. We learn Recurrent Neural Network (RNN) /Sequence Model, which allow translation or trigger word (like "Hey Siri!"). It's a completely different beast than CNN seen in Course 4. Again, nice videos and explanations, and well-designed useful programming assignment (TensorFlow/Keras and numpy)
By OMAL P B•
I Highly recommended this course on Sequence Models. The course is easy to follow as it gradually moves from the basics to more advanced topics, building gradually. Andrew Sir makes the cocepts behind the scenes about LSTM GRU etc very easy to understand. Assignments are great, extremely well designed. Best assignments you will ever get to practise and learn.
By Hardik A•
The kind of simplicity with which the course is explained and the amount of knowledge gained is worth the hard work of many months! . . I would like to thank the whole Coursera team and Sir Andrew Ng for creating such a wonderful platform and a big shout-out to all the mentors and community who have replied to the most basic queries in the discussion section.
By Bing H•
Home work assignment notebook has a quick time out issue. It's quite annoying since most of the assignment has lots reading material to fully understand the topic or method. Often the notebook just time out and has to be restarted before move to the next section. Hopefully, it can be fixed or improved.
Overall a very good course to learn about sequence model.
By Jiandong S•
It took me a longer time to finish the course due to busy schedule. But I found it totally worth the struggle to work on the course material. Sequence modeling and processing is an new area to me. The course taught me some basic concepts and gave me a chance to lay hands on through programming exercises. I feel a lot like the topic particularly NLP. Thanks!
By Quentin G•
Très largement plus difficile que tout ce qu'il y a eu auparavant. Un véritable apprentissage et un plaisir surtout sur le Trigger Word Detection qui était très intéressant.
Totally more difficult than anything before. I've acquired true knowledge that I'm very proud of. It was a pleasure, especially for the Trigger Word Detection which was very interesting.
By Lucas O S•
Exercises too basic. Better to do something simpler from scratch, them fill in the blanks on statements like "define a to be a boolean variable initialized to True", and run a bunch of other cells with imported code that hides the actual complexity. These kind of exercises does not add anything to the student. Content of Andrew's lessons is great, however.
By Neelesh A•
This course helped get a good intuition as well as further specifics of voice recognition which is what I am most curious about.
I think they have put together a right mix of Conceptual puzzles, Implementable codes and Lucid lectures to help one learn and advance one's understanding and intuition framework to build on top of subsequently.
Great work guys!
By Gaurav K•
Thank you Prof Andrew Ng for sharing the knowledge and experience. It has been truly a great learning during the course specialization. And I always admire the way you structure the course and teach the advanced concepts with such an ease. With the power of AI, we as a community try to solve real-world challenges for better life. Thank you so much!
By Shifeng X•
awesome! Thanks to Andrew and his time to deliver this wonderful course. It really give me a very good sense about what's going on with the Deep Learning in several areas. The course material is prepared in a way that it's very easy to catch up. Just one suggestion, this sequence model session is too short, lots of topics haven't got well deployed.
By Martin B•
Very very interesting but it's a lot more difficult than the other courses. I did it out of sequence (no pun intended) (i.e. I skipped Convolutional networks to go straight to RNN, because they interest me more).
That wasn't the correct move. I barely knew anything about Keras, the exercises took a LOT more time. Still, it's a wonderful course.
The class lectures are easy to follow and programming practices showcase a good variety of interesting implementation/practice of sequence models. Not only does it introduce how models work and are constructed but also illustrate how those models can be applied to real-life problems (e.g. voice detection in smart home, music generation...etc.,).
By Dhruv B•
I have earlier completed first 3 courses of the Deep Learning Specialization. This course widens the horizon of deep learning applications. Through the assignments, I have gained confidence in understanding the model architecture and the underlying theory behind it. I recommend every to enroll for this course if they want to learn how RNN works.
By Wei H•
Great lectures on the intuitions behind RNN and their applications in real life. It requires some self-exploration to complete the programming assignments related to Keras and tensor, but the structure of the assignment is very good. I have learned a lot from this lecture and it helped me to understand the language of the field of deep learning.
By Pablo G G•
Awesome course, with lot of detailed and well guided practices! After finishing all of them I went directly to look on GANs and Transformers and with the knowledge gain thanks to Andrew Ng and his team, I set up my local Jupyter with tensorflow-gpu and start using state-of-the-art machine learning! Check out paperswithcode for awesome projects!
By Nikhil D K•
I decided to do this course after reading the first few pages of the Deep Learning book by Goodfellow, Bengio and Courville. I'll probably go back to that book now, to reinforce what I learnt from this set of 5 courses. I plan to also get more practice with the programming frameworks. The Tensorflow specialization is probably my next conquest.