Fun course, like the rest in the series. I hadn't seen neural networks applied to time series, so that was really worthwhile to learn.

There are still some rough edges and a few parts of the labs that aren't addressed in the videos.

I really enjoy the format of the courses which emphasized a lot of experimentation with networks and provided opportunity for trial and error.

If one has seen LSTMs from the previous course and has been exposed to time series there is a little conceptual material to learn from this course, but of course the focus is on tensorflow/keras programming. Highlights were learning how to include lambda layers (which allow one to execute arbitrary code in the network) and how to automate selection of the learning rate.

Very nice explanations and videos, so I really like it. Basic for timeseries covered and a lot of detailed explanation provided how to apply TF to forecasting. However, quizes are too trivial and doesn't measure understanding of material IMHO. It will be great if separate data set will be used to control understanding of material and motivate to practice more with TF.

I learned some time series models and processing methods, but I think this course is too simple and too shallow, for example, there is no prediction of the situation that contains complex features, and how to combine autoregressive features with other features. Models in this course are very popular and are used by everyone, there is no deep stuff

A really helpful course for those who have just started their journey in the field of machine learning and AI. Strongly recommended for gaining great insights within the field, though all the materials covered are quiet shallow and practical. Use this as a way of learning the tools, not for mastering the theoretical background behind it.

I really wish you could extend the course to multivariate time series prediction, as well as into multivariate time-series multiclass classification. That was indeed the reason why I wanted to learn more about sequence models, as I will be using them in my research on decoding EEG signal. apart from that, it's an excellent course

Sunspot example was good, but i preferred to have few more examples to exhibit different types of real data, like data having both seasonal and also trend. Though the concept is well explained using synthetic data confidence on the subject would have more if had real data for all different types.

Thank you for this very interesting and informative course. I really enjoyed the simplicity in explanation and the hands-on implementations. One thing that I think will improve this course further is to add more intuition and explanation of using particular structures like CNN followed by LSTM.

The awesome learning experience with Coursera. So far, I have completed up to the Deep learning specialization. All the courses are well structured with self-learning, live quiz, and assessment. The trainers are good, connect to students, and answer questions. Happy learning.

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.

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.

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.

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 :)

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! ;-)

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.

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.

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.

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.

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.

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!

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.

Loved it.

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.

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.

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.

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.