Chevron Left
Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization(으)로 돌아가기

deeplearning.ai의 Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization 학습자 리뷰 및 피드백

4.9
42,401개의 평가
4,526개의 리뷰

강좌 소개

This course will teach you the "magic" of getting deep learning to work well. Rather than the deep learning process being a black box, you will understand what drives performance, and be able to more systematically get good results. You will also learn TensorFlow. After 3 weeks, you will: - Understand industry best-practices for building deep learning applications. - Be able to effectively use the common neural network "tricks", including initialization, L2 and dropout regularization, Batch normalization, gradient checking, - Be able to implement and apply a variety of optimization algorithms, such as mini-batch gradient descent, Momentum, RMSprop and Adam, and check for their convergence. - Understand new best-practices for the deep learning era of how to set up train/dev/test sets and analyze bias/variance - Be able to implement a neural network in TensorFlow. This is the second course of the Deep Learning Specialization....

최상위 리뷰

XG

Oct 31, 2017

Thank you Andrew!! I know start to use Tensorflow, however, this tool is not well for a research goal. Maybe, pytorch could be considered in the future!! And let us know how to use pytorch in Windows.

HD

Dec 06, 2019

I enjoyed it, it is really helpful, id like to have the oportunity to implement all these deeply in a real example.\n\nthe only thing i didn't have completely clear is the barch norm, it is so confuse

필터링 기준:

Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization의 4,461개 리뷰 중 4001~4025

교육 기관: James D B

Jun 23, 2019

Probably a little too follow your nose at this point in the specialisation. But none-the-less very good. Would give 4.5 stars if that were an option.

교육 기관: Christoph S

Mar 03, 2019

Still some flaws + inaccuracies + video sequences that should be cut out. I think the organizers should really do it as people are now paying for it!

교육 기관: Teodor C

Dec 28, 2018

Last Tensorflow assignment has some output typos and bugs when using operators like @ and +. Course was ok, but that assignment took me way too long.

교육 기관: HongZhang

Jun 14, 2018

Great course to deepen my knowledge after first course. However, I would like to access more programming exercise for practice. That will be perfect!

교육 기관: Daniel E B G

Aug 26, 2019

I think this course would benefit from a little more explaining. There are a lot of new concepts and some explanations were too quick in my opinion.

교육 기관: Stephen R

Oct 26, 2018

Enjoyed this course, especially the material that goes a bit deeper (different optimization methods, parameter tuning) and the intro to TensorFlow.

교육 기관: Huang C H

Nov 24, 2017

Less exciting than the first course, but this course is important to understanding the parameters that could affect a neural network's performance.

교육 기관: Youssouf B

Apr 22, 2019

what I did recognize in the deeplearning specialization that there are now further reading suggestions or reading syllabus like the other courses.

교육 기관: Harsh T

Feb 26, 2019

This course is one of the best course for good understanding of hyperparameter tunning.

And also let you know the effect of various hyperparameter.

교육 기관: Nicolás E C

Apr 09, 2019

Nice course, TensorFlow might need some more in-detail explanation because it's a different than programming with Python, but it was really nice.

교육 기관: Vinicius J S

Aug 08, 2018

Nice course and nice the Tensorflow introduction, but there are errors on the lecture and on the final test. Be aware to use the forum some times

교육 기관: Collin J O

Mar 15, 2019

Valuable lessons, but the tensorflow lesson + assignment at the end was a bit vague and hard to follow to the point of passing their test cases.

교육 기관: Giuseppe N

Jul 09, 2018

It's very good, but I would have spent more explaining the difference between adding layers and adding neurons, and how to decide the next move.

교육 기관: Jeremy Z

Dec 11, 2017

a few of the examples and expected output for the programming exercises seemed not to be correct. otherwise great course. highly recommended.

교육 기관: David A S

Sep 27, 2017

Good course. Kinda skips over hard bits which only leaves one with more questions. Hopefully these details are recovered in the later courses.

교육 기관: Dinh T T

Feb 09, 2019

It's a wonderful course because it provides me how to improve deep neural networks and delve to some techniques to gain good hyperparameters

교육 기관: John S T L

Feb 01, 2019

Would have given 5 stars if the Jupyter exercise did not give me too much of a hard time looking for errors in syntax. Overall, great lesson!

교육 기관: Parag P

Oct 19, 2018

Loved the easy to understand explanation given by Prof. Andrew Ng for some of the most complex concepts in Deep Learning like Regularisation.

교육 기관: Daehee K

Nov 05, 2017

This class is very helpful for understanding parameters of ML except week 3 class and assignment for Tensorflow which is not fully explained.

교육 기관: Xiaochao G

Dec 25, 2017

I don't understand tensorflow mechanism and when to use what function. Should I stop to learn more tf or just move on the following courses

교육 기관: Nataliia K

Oct 28, 2019

Quite ok, but programming assignment was mostly copy-paste style. I am not able to repeat something similar independently after the course

교육 기관: Maximilian B

Sep 25, 2018

A lot of great concepts covered in the lectures but only few were explored in the assignments. The assignments seemed fairly simple to me.

교육 기관: Vanja T

Sep 24, 2017

There were grading results that seemed wrong - I've submitted report on grading to explain details. Other than that, the course was great!

교육 기관: Aditya S

Oct 05, 2019

Good course. However expected some more mathematical proofs for some of the ideas like bias correction and exponential weighted averages.

교육 기관: Prerna D

Sep 07, 2019

Very good course. All the concepts explained very well. I just feel programming assignments were too easy, they could be a little tougher