Comentários e feedback de alunos de Sequences, Time Series and Prediction da instituição deeplearning.ai

Even worse than the NLP course. Week 1~3 contains nearly no new material for tensorflow. It's just some replicated knowledge from previous courses. Studying synthetic data is good, but is off-topic for a tensorflow course. The course should focus on models and model structures for different types of time series data. My biggest complaint is that this course does not cover even the basic knowledge required by the tensorflow certificate exam (as advertised). Where is the multivariate time series forecasting? This is the most important part of the exam but the course totally neglects that.

Like the previous course, this is not a four-week course but a collection of short videos that can be watched in one morning. The first week (actually the first hour) provides interesting insights about time series but the rest of the weeks (hours) are a quick review of code snippets. The pace set by a sequence of one-minute videos is excruciating and makes it difficult to follow the lectures. In addition, there are no practical assignments, just some trivial quizzes.

I do hope that the deeplearning.ai team could spend more time polishing the materials instead of just throwing the Tensorflow docs/sample codes and going through them superficially. Please also change the instructor as I really doubt his professionalism/experiences in ML practices despite his titles. Please, please don't ruin your brand, deeplearning.ai. I wish to see more in-depth courses like the ones taught by Andrew.

Extremely shallow and sloppy made course. It is sad to see that the optimization done in the neural network is at the very least non-robust (if not totally random). The techniques used are simple illustrations that one can find better in youtube videos for free. The fact that people have to pay for this course is basically a scam, you should be ashamed of yourselves.

Maybe I had wrong expectations from this course. But to me it felt like the material in this course was extremely superficial. I was hoping to learn something, but it turned out to be a very basic overview of the material. Everything boiled down to "compile + fit" without the explanation of nuances associated with time-series settings.

The last two parts of this 'specialization' were pretty much useless. Here's some code, let's look at the code three times, let's take a kindergarten quiz, let's look at the same code again, here's the answer you can copy if you bother doing the exercise.

This is a quick introduction of using TensorFlow for prediction without any explanation for helping students understand the codes, the rationale, and the technical details we need to know for doing practice in daily work.

Gives a very shallow understanding. You can easily pass the quizzes without even needing to go through the colab code notebooks. This is unfortunately quite a good example of 'money can buy you a certificate'.

Extremely shallow ML course, with certain videos showing nothing more than running a few code snippets. More depth and explanation could go very far in improving the overall experiece

Really disappointment. Wonder what is purpose. After few videos it seemed like synthetic data is created just to create course. Lost interest very quickly

Extremely shallow. It's just to have an initial idea but not in depth.

To be honest course content was realy week.