AA
Invalid date
Assignment in week 2 could not tell the difference between 'a-=b' and 'a=a-b' and marked the former as incorrect even though they are the same and gave the same output. Other than that, a great course
YL
Invalid date
very useful course, especially the last tensorflow assignment. the only reason i gave 4 stars is due to the lack of practice on batchnorm, which i believe is one of the most usefule techniques lately.
By Rachana O
•Aug 17, 2020
Can be done in more interesting manner.
By Mark L
•Jul 16, 2020
great superficial intro to the content
By jerome c
•Oct 14, 2018
Need more training on Tensorflow, imho
By Juan J D
•Sep 11, 2017
tensorflow subject was to superficial
By Weeha G
•Jul 25, 2021
Assignment of week 3 is toooo brief.
By SATHVIK S
•Jul 26, 2020
Can dive deeper into the mathematics
By Trevor M
•Nov 23, 2020
good lectures terrible exercises
By Maisam S W
•Oct 4, 2017
I still find tensorflow hard.
By Andrey L
•Oct 1, 2017
week 2 was extremely boring
By Cheran V
•May 9, 2020
Outdated with Tensorflow 1
By QUINTANA-AMATE, S
•Mar 11, 2018
Again, nice videos but not
By Matthew P
•Sep 3, 2021
Focused a bit on minutia.
By Adam G
•Jul 11, 2020
Multiple grading issues.
By Chaitanya M
•Jul 1, 2020
could be more engaging
By José A G R
•May 23, 2023
Estoy muy emocionada
By Cory N
•Jan 8, 2020
Update for TF2.0 :)
By Алексей А
•Sep 7, 2017
Looks raw yet.
By Ilkhom
•Mar 21, 2019
awful sound
By Akhilesh
•Mar 14, 2018
enjoyed :)
By Sai R
•Nov 10, 2022
Good
By zhesihuang
•Mar 3, 2019
good
By CARLOS G G
•Jul 14, 2018
good
By Hoàng N L
•Feb 12, 2019
N/A
By KimSangsoo
•Sep 17, 2018
괜찮음
By Maximilian S
•May 7, 2022
This is a nice but very basic introduction to the practice of DL (the last week about tf is nice). However, the assignments are way too shallow! In the assignments the students are "spoon-fed baby-food"... one can solve almost all exercises without thinking and without having understood anything (it is mostly solvable by copy&paste).
For instance, I have learned the most in the final assignment when it did not fully work and I forgot a tf.transpose(..) and I actually had to think about what was happening.
Anybody applying to our group who presents this course as evidence that they know about the contents will not be taken seriously (and rightfully so!) -- thanks for a very quick way to sort out useless applications (anybody presenting a certificate for this course in public).
The assignments could also be auto-graded by using the format of any programming competion (specifying the input-output relation, providing an input, and giving the student total freedom in how to implement the solution), e.g. like in the famous advent-of-code. Then the course would be harder (but way more valuable!) -- however, coursera won't get enough paying subscribers that way I assume.... oh what a pity.