Really like the focus on practical application and demonstrating the latest capability of TensorFlow. As mentioned in the course, it is a great compliment to Andrew Ng's Deep Learning Specialization.
I really enjoyed this course, especially because it combines all different components (DNN, CONV-NET, and RNN) together in one application. I look forward to taking more courses from deeplearning.ai.
創建者 FERNANDO D H S•
Good course, I'd liked more the evaluation methodology of the first two courses on the specialization: questionare and coding excercises. Although here we have ungraded excercises it is more rewarding to see that effor translated to the grades.
Thanks again and great courses.
創建者 Roghaiyeh S•
I was looking for a basic step by step guide to Tensorflow and this course was amazing. I can now use my knowledge in DL from Deep Learning course better. The instructor was great, explained everything clearly. I think it was better if there was programming assignments too.
創建者 Sharad C R•
This course enables you to start using TensorFlow as an off the shelf tool. The idea of this course is to make you comfortable with using TensorFlow for predicting time series data. Theory and statistics behind dealing with such data is beyond the scope of this course.
創建者 Amarendra M•
I think this course will be of great help if one has worked on time series data. I was a complete novice to time series, and found it difficult to relate. However, I learnt a great deal about the tensorflow technical aspects.
Thanks Lawrence for making it so easy :)
創建者 Alfonso C•
The course is great, but I would have loved knowing more about how to deal with multivariate time-series, data sets with many time-series, variable prediction horizon etc.
Hope a more advanced course on time series forecast with tf.keras is under construction! ;-)
創建者 Raphy B•
The exercises are not so well constructed compared to the other courses in this specialization. Overall, the content is "spot-on" (pun intended) when it comes to explaining time-series and what methods we can use to approach to these problems.
創建者 Yogendra S•
It was great to start with synthetic data than applying the model to the actual data. It would have been great if assignments were mandatory and new case studies could be practiced. Otherwise course is great to do hands on with tensorflow.
創建者 David R C S•
before this course, I didn't have knowledge about time series and the problem with the course is I end with the same lack of knowledge because it's more like a tutorial about how to build your NN that a understanding of what is going on.
創建者 Yingnan X•
The homework exercise seems to heavily overlap with the demo notebook that I can simply copy and paste the code into the exercise notebook. It would be great if in the future the exercise can be a little harder and involve more thinking.
創建者 Shiladitya P•
I learned the best practices for forecasting using statistical techniques as well as deep learning networks in this course. One point for improvement is to focus on a few multi-variate examples with code, which was absent in the course.
創建者 Adnan D•
It was good totally, but I think the assignments weren't enough also I expected the multivariate time series to be covered but it wasn't, I'm waiting to see this teacher next course soon I wish for better assignments and a cool topic!
創建者 Александр З•
I would like to have more info on window and batch sizes - seems to be pretty important values to work with, but they are not covered in depth.
In general, greate course that shows how to prepare sequences, feed them in to NN.
創建者 Vahid N•
It is very easy to follow this course. I wish some function/object options and arguments (such as why we use Y^hat (hat is usually reserved for estimated values) and not Y in LSTMs) were explained in more detail for curious readers.
創建者 Neelkanth S M•
As with an machine/ deep learning model, data preprocessing is the most underrated part. Taking this course exposes students to various pre-processing nuances that are helpful in training a deep learning model.
創建者 Tobias L•
Nice and short introduction to time series handling in Keras. As with the other courses, this is a simple hands-on course. I therefore recommend to take the DeepLearning Specialization before this course.
創建者 WALEED E•
The course is fantastic. It was a bit short and with some hyperparameters tuning focus, it could have been great. Also, it seems that it is biased to show that LSTM is always superior to RNN networks.
創建者 mehryar m•
I'm so glad to take this course and build my knowledge regarding time-series data and modern approaches to create prognostic models. Thanks to Andrew Ng and L. Moroney to provide this course.
創建者 SIDDHARTHA P•
Few hands on programming assignments could be better for experience as was the case with starting two courses. Overall good course and the structure was well laid. Thanks for building it up
創建者 William G•
Though I feel some aspects of this course did not delve deep enough into the explanations of some functions, the course helped me understand how to use models for time series problems.
創建者 winniefred m b•
taking this course was undoubtedly a better idea than endless scans over tensorflow documentation and other books. I am glad I got to do this course, wish I had taken this up earlier
創建者 Hyungmin S•
I wish there were more detail explanation about hyper-parameter tuning when we define NN Models.
other than that, this course was great and gave me lot of insights. Thank you.
創建者 Yongqing X•
I'd like to learn more about algorithmic principle（Although some Andrew‘s class link is attached. ）why not explain the principle combined with the real example
Wish there were graded programming exercises. The quizzes has questions not relevant to the goal of the lesson ex What is the seasonality of sunspots.