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
stars
42,297개의 평가
4,513개의 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.

AM

Oct 09, 2019

I really enjoyed this course. Many details are given here that are crucial to gain experience and tips on things that looks easy at first sight but are important for a faster ML project implementation

필터링 기준:

Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization의 4,446개 리뷰 중 4076~4100

교육 기관: Keanu T

Jun 26, 2019

I wish it went a little more in-depth with softmax classifiers but I can find that online so it's good.

교육 기관: Byron M

Apr 09, 2018

The final assignment didn't have the right instructions, a lot of misleading comments and instructions.

교육 기관: Matías L M

Oct 30, 2017

The professor is really good at explaining. The projects got more interesting than in the first course.

교육 기관: Per K

Oct 03, 2017

Get you to a more practical understanding of deep learning. The introduction to TensorFlow is valuable.

교육 기관: LEO L

Jul 31, 2019

All is good except the submission part, sometime return submission failure without specifying a reason

교육 기관: Hamza E B

Jun 22, 2019

Great Course ! I learned a lot, but I would have preferred another Framework though (like Pytorch) ...

교육 기관: Qingyun W

Jun 06, 2019

Some typos in the programming assignment is still not fixed (Mentioned in top posts in the discussion)

교육 기관: ryan m

Oct 08, 2018

a very informative course, I was introduced to Tensorflow through this course... I absolutely loved it

교육 기관: Dan C

Feb 28, 2018

I had a bug in my compute_cost function that caused cost to spiral but the grader did not catch it....

교육 기관: Lin Z

Mar 28, 2019

interesting introduction about deep neuro networks with examples on how to use Tensorflow framework.

교육 기관: Marijan S

Sep 09, 2018

I learned very useful info, but the last programming asignment with tensorflow was a pain in the a**

교육 기관: Apoorv A

Feb 04, 2019

I think things could have been more difficult. Currently it is way to easy to pass the assignments.

교육 기관: Potnuru A

Jun 18, 2018

This course provides more tips and ideas toward deep learning and introduces tensorflow. Worth it.

교육 기관: Faniry R

Mar 14, 2018

Best explanation ever! Exercises should be made available even without a possibility of submission

교육 기관: Tirumala R M

Jan 24, 2018

Well explained the need of regularizations. Also python was best language to get assignments done.

교육 기관: Siddhi V T

Sep 19, 2019

An awesome course for someone who wants to learn how to tune the hyperparameters of their models.

교육 기관: Alexey V

Mar 18, 2019

Ran into bugs with some assignments, for example week 7 was not correctly calculating final model

교육 기관: Tamás J

Jun 14, 2018

Jupiter Notebook fails too offen! I had to close the window, start again, which is very annoying!

교육 기관: Chen X

Mar 27, 2018

It's fun they assume you know human error rate or optimal Bayesian. It's very rare in real world.

교육 기관: Alejandro R

Oct 26, 2017

I miss the end of video quizzes, but can't rate it lower than 4 because this course is excellent.

교육 기관: Digvijay S R

Jan 18, 2020

perhaps more practice of tensorflow is required. The tensorflow module also needs to be updated.

교육 기관: Isaraparb L

Jul 15, 2018

Some of the math may be hard to grasp, but the course gives a lot of useful information overall.

교육 기관: Amine B

Apr 25, 2018

Great course, very complete and instructive! The programming exercices should yet be less guided

교육 기관: Sebastian R C

Mar 22, 2018

I think the material is quite basic, since it is an specialization, we could go a little deeper

교육 기관: Kasper J

Oct 01, 2017

Overall a very good course. However, I was hoping for more material on programming frameworks.