Mar 22, 2020
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.
Jun 07, 2020
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.
교육 기관: Asad K•
Jul 31, 2019
The first week has some interesting discussion of time series data and some traditional non-ML methods for forecasting, but beyond that the course quickly divulges the all too familiar weaknesses of this specialization; lack of depth, elementary discussion, weak insight into common problems that arise during training models, and extremely poorly written quizzes that don't test the learner's gain of knowledge or skills in any meaningful way.
My biggest complaint to the instructors and the team is that for months this specialization promised the last course will discuss the WaveNet model, but the course didn't even do a cursory survey of it (In week 4, the instructor adds a Conv1D layer but doesn't even discuss the causal padding and completely skips dilations, etc, so that in effect there isn't even discussion of a single layer from WaveNet model). Sigh !
교육 기관: Fengjun W•
Aug 18, 2019
Finally, wasted my weekend and 40 euros to finish this shitty specialization. I really dont know the target audience of this specialization. If you have no background of deep learning, going through some code snippets without any explanation wont help you at all. you can't know anything behind it. If you already have some knowledge, you will find nothing new and more in this course. 1) The materials are so shallow and without any depth, just reading the slides and codes with errors. Only some high-level keras APIs are covered. The official tensorflow tutorial is much better. 2) The test questions are of no value at all, it cant test any your understanding whether about deep learning or the tool tensorflow. The assignments are poorly designed, the answers contains errors. 3) I strongly doubt the instructor, I think he does not have much ML experience. Please don't waste your money and time on this specialization. If you want to learn deep learning, go to cs230; cs231n for computer vision; cs224n and cs224u for NLP; cs20 for Tensorflow.
교육 기관: Irina G•
Aug 02, 2019
Very weak course, shallow, lacks content. Can be "learned" in a few hours, not weeks. Really hoped to see a working ML model for a time sequence, but the examples shown in this course do not demonstrate why bother with ML. If these examples were middle-school home work, they would be graded D+(keep trying or better use other methods). The instructor doesn't come across as an experienced ML practitioner.
교육 기관: Steve H•
Aug 07, 2019
Very superficial presentation of the material, and disappointing content given all the initial hype. Whatever happened to working with WaveNet? The 4 weeks to complete the course is a massive over-estimate. Expect to spend not more than a day going through the course. Quiz questions are very low value and do not test any understanding.
교육 기관: Kaan A•
Aug 24, 2019
Unfortunately, These whole Specialization didnt match my expectations. I finished whole Deep Learning Specialization and I LOVED IT. Before starting this one I had very good feeling about this specialization; however I learned very little. Most of the videos are like "this code does this and this code does this and this line does this and this function does this etc. " . A bit disappointed, but still learned some.
교육 기관: Jussi H•
Jan 07, 2020
I wanted to like this specialization, but I just cannot. My expectation was that this specialization would complement Andrew Ng's excellent Deep Learning specialization, but it does not. Whereas the DL specialization taught you best practices and a systematic approach to improving models, this specialization throws all of that out the window. The architectures are downright silly in some of the examples. If you want to learn TensorFlow, you would spend your time more wisely by working through the official TF tutorials, which are pretty good.
교육 기관: Charlie C•
Dec 22, 2019
No concrete knowledge, no solid explanation. Just some demo.
교육 기관: Yaron K•
Sep 30, 2019
A step by step explanation of how to use TensorFlow 2.0 for building a Neural network for sequences and time series. With detailed examples of code and of how to choose hyper-parameters.
교육 기관: Marghoob K•
Aug 03, 2019
This was really a beautifully designed course. They didn't focused on teaching too much of thing at once but build up the base slowly and strongly for better understanding.
교육 기관: Parab N S•
Sep 14, 2019
An excellent course on Time Series and Sequences by Laurence Moroney. Explained how to use CNN, RNN and DNN together to bring the nest out of time series prediction.
교육 기관: Subhadeep D•
Jul 31, 2019
Quite a good light-weighted course on Time Series and Prediction. It was quite helpful for people like me who are seeking ways to implement the concepts.
교육 기관: Silviu M•
Sep 02, 2019
The material is great and the presentation elevated and professional. Few thoughts nonetheless: a) i know time series, came here for specific advice on how to tune models. I was extremely disappointed. Stationarity is mentioned at the very beginning but then it fades as if it was completely irrelevant to ML. b) there is more than one contradiction in the presentation. MAE is going up yet the presenter says that it got better??? That I think would be really confusing, particularly for novice learners. c) black boxes: I acknowledge that there are so many decisions and choices one needs to make when setting up a training model. Wouldn't it be relevant to highlight them and explain how different decisions impact the outcome? This course was failing on that.
교육 기관: David R•
Nov 11, 2019
It's a bit of an insult to call this thing a "course". The entire video material is maybe a bit over 1 hour for the entire "4 weeks". The quizzes (1 quiz per week) are ridiculously easy, and the (ungraded) exercises are basically - "do what we did in the lecture, only from memory".
The material itself is good, but doesn't go in depth. They introduce Huber loss, and then tell you to go read about it in Wikipedia.
Overall - low quality. Would have been great as a first week in a real "mini course" (DeepLearning specialization style), or one lecture, in a real academic course.
교육 기관: Kirill S•
Mar 23, 2020
A lot of repetition of the same methods, no clear indication on how exactly to tune the chosen NNs (for instance, how to select their order, how to tune optimzers' parameters, etc) + extremely simple quizes. In general, it looks like this whole specialisation was designed just to earn some money on a existing deeplearning.ai brand. Huge disappointment.
교육 기관: james b•
Mar 28, 2020
No graded exercises at the end of the practicals. Some of the quiz questions seems to be based more around general python and in 1 situation around the presenters only thoughts. Some information about estimating optimal learning rates was incorrect and misleading
교육 기관: Alvaro M A N•
Jan 03, 2020
Personally I loved this course, I had a previous knowledge of this topic, because it's one of my favorites topics (very related to IoT analysis data). And here I've learned various top technics suchs lambda layers, or that we have to split in training, validation and testing periods the data. This is something that you don't see in many books or manual about time series with tensorflow. And finally I've learned very useful libraries that I even didn't know that exists like tf.keras.dataset, that makes so easy to give format to the data, before you had to write more code. So with this information I can write more effective and efficient code! Thanks Laurence and Andrew from Perú!
교육 기관: Richard S•
Sep 15, 2019
This course was my ultimate motivator and goal for taking the specialization as I am doing work with time series. Very interesting to learn a traditional statistical approach, then apply DNNs, RNNs, LSTMs and CNNs to time series prediction. Even though just scratching the surface, I can apply knowledge from this course and specialization immediately.
Thank you Laurence and Andrew for a fantastic course and specialization! I am inspired and motivated to dig deeper into the theory of NNs and their application with further courses and projects.
교육 기관: Saif H•
Aug 28, 2019
It was a brilliant course , I thoroughly enjoyed learning various aspects and techniques of Deep Learning techniques and in the process also learned a lot about TensorFlow . As mentioned by LM , its the first step and I'm really to have taken that first step.
One of the issue with the course has been the quality of audio, all the other course I have done on Coursera had very clear and audible voice over , however with this course I have struggled to hear with the audio, hopefully this can be addressed in future course.
교육 기관: Hannan S•
Oct 28, 2019
First of all, the course was amazing! I found it great for the following reasons:
- Laurence Moroney (Instructor) was very professional and clear while delivering the knowledge
- The introductions by Andrew NG were really nice
- Easy to understand codes and understanding of thr underlying principles
- Varied topics such as CNN, NLP & Time Series
- Very insightful by providing expert opinions about different ways of model optimization
I really enjoyed the course and I thank the instructor for the same :)
교육 기관: Amandeep S•
May 09, 2020
Great for learning the basics! Love the instructors. They have a great attitude, and their commitment just inspires us to try to give something back to the community as well.
The exercises were a bit not well-thought of. The data manipulations seemed too specific. Besides, reading the Numpy/Keras documentation is not always worthwhile for beginners. So that was a bit confusing. But if you are good at Python, that won't be a problem.
Keep up the good work, the deeplearning.ai team!
교육 기관: Michael•
Aug 17, 2019
I enjoyed the last course of the practice in tensorflow. There is a lot of note books to work with, the teaching was good and good referencing. Simple to understand, even though we might require more notes and also materials to work on the local jupyter notebook. Some simple code could be a night mare as you are using windows machine, linux, anaconda. As the courses progressed, there are more and more references to work with. Looking forward to the next set of courses.
교육 기관: Andrés R•
Jan 26, 2020
Ok, this course was amazing, cause i pass a big large course in Udemy about Data Science for get a right way to complete my master degree tesis, and it was not enough for my, this course will help me to use my own data set that have been streamed for some sensors to analysed and predict them, before this course i don't know that CNN and LSTM is a right way to work with time series but, nowadays i know that is a good way, congrats Laurence and Andrew.
교육 기관: Ravi P B•
Mar 15, 2020
Nice experience taking this course. Precise and to the point introduction of topics and a really nice way to start programming the models without going much into theory and a comprehensive and nice way to learn tensorflow framework. Mr. Laurence Moroney Sir has been excellent in all the courses and the conversations with Andrew sir are chilling as well as motivating. So its been a very good experience to take this specialization and learn tensorflow.
교육 기관: Gabriel A S Z•
Jul 07, 2020
Guys you are the best, i commented to Laurence to about six months ago that i finded my vocation with your course, and with the firts course of this specialization i didn't understand anything and i did the Deep Learning Specialization and i am really fascinated with AI and deep learning. By the way I am a mathematician and thank to you i am a AI research with TensorFlow as a tool for coding and building DL and ML models.
Really Thank you
교육 기관: Andrei N•
Sep 21, 2019
Very detailed step by step tutorials of using Tensorflow with lots of effort to make things as easy to understand as possible. Especially, examples of generation a time-series pattern simulations looks very thoughtful and helpful for the course topic. A little lack of theory comparing to other courses by deeplearning.ai. Quizzes are quite undeveloped. But that is understandable, because the main goal of the course to introduce Tensoflow.