Dec 1, 2020
I learned so many things in this module. I learned that how to do error analysis and different kind of the learning techniques. Thanks Professor Andrew Ng to provide such a valuable and updated stuff.
Jul 1, 2020
While the information from this course was awesome I would've liked some hand on projects to get the information running. Nonetheless, the two simulation task were the best (more would've been neat!).
By Xiang L•
Apr 26, 2021
This session might not be very helpful for people from different backgrounds such as non-industral level application of deep learning.
By Lars L•
Dec 30, 2017
Course materials need some cleanup. Were a number of audio blips, in the video. Material was good but just didn't seem as polished.
By nitin s•
Jun 25, 2020
Decent learning. Though quite some stuff, I felt as repetitive and obvious.
I wish there was some programming exposure as well here
By Taavi K•
Nov 29, 2017
Too short on its own (took half a day to go through the whole thing), could have been combined with Course 2 of the specialization.
By Farid A•
Jul 18, 2022
- could have been better with more hands-on excerices or assignments.
- the assignments were quite hard compared to the lectures
By Jean-Michel P•
Jun 29, 2021
I feel like this course should be broken down and included in the other courses to get better context within these other courses.
By Raghu t D•
Aug 6, 2018
this session was good it would be more better if they provided the code of them..so that we could be abke to learn more from them
By Denys G•
Nov 23, 2017
Felt a bit rushed, each video was full of good tips but personally I think each video should have been a jupyternotebook instead.
By Massimo A•
Nov 18, 2017
More theoretical than the other courses in the specialisation but still very high quality.
Short but with a lot of information.
By David P•
Oct 17, 2017
Not nearly as good as the first two courses. These two weeks should probably be added into the second course at some point...
By Oliver O•
Oct 16, 2017
Would like more applied discussion and for it to be Longer. In particular I would like to see a discussion on class imbalance.
By Shuai W•
Sep 19, 2017
The content of this course is a bit too little for me.
However, it provides useful guidance for my projects. Much appreciated!
By Gary S•
Sep 15, 2017
Not nearly as valuable as the first Deep Learning course. And the questions posed in the quizzes seemed far more subjective.
By Pejman M•
Oct 21, 2017
Programming practices with TensorFlow should have continued in this course. Unfortunately, these two weeks were all talking.
By Nithin V•
Jan 3, 2021
Need more quizzes, assignments to deepen the understanding, But otherwise thank you Andrew Ng for presenting this material
By Panos K•
Apr 18, 2021
The pace of the first part of the course was too slow. The second part (from Transfer learning onwards) was much better.
By Mustafa H•
Jul 16, 2018
This course does discuss interesting and important subjects but I feel it can be combined with course 2 of this series
By Ahmed A•
Jul 10, 2018
course is very good have a lot of important theory, it will be amazing if become 3 weeks with programming assignments.
By Kevin Q•
Mar 19, 2018
lot of issues with assignments and ambiguous quiz questions this time around, not as polished as other Andrew courses
By Arghya R•
Sep 19, 2017
Could have more case studies and above all. Also programing assignments on self driving car could have been better
By Okhtay A•
Apr 5, 2020
A bit too free form compared to the other courses in deep learning specialization, but maybe that was the goal.
By Masih B•
Jul 18, 2020
This course could be way more better, if it also focused on codeing with tensorflow (like the previous course)
By Janet C•
Jun 29, 2019
Overview of the machine learning process. No projects or sample code to actually organize the ideas into code.
By Aniruddh B•
Apr 16, 2020
Very nice, but I don't believe the content merits a full course. It could be integrated with courses 1 and 2.
Feb 28, 2018
To much talk but understandable. Need something like programming examples with different data distributions.