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
42,485개의 평가
4,534개의 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

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

NA

Jan 14, 2020

After completion of this course I know which values to look at if my ML model is not performing up to the task. It is a detailed but not too complicated course to understand the parameters used by ML.

필터링 기준:

Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization의 4,466개 리뷰 중 4201~4225

교육 기관: Alberto S

May 20, 2018

By itself, not really a couse. It should be part of the first one.

교육 기관: Muhammad W

May 12, 2018

few mistakes in course assignment but overall good course material

교육 기관: Michael F

Apr 20, 2018

The programming assignments were too easy, otherwise good content.

교육 기관: Siyu Z

Mar 19, 2018

A good course. I get familiar with the idea about hyperparameter.

교육 기관: Carlos P

Feb 11, 2018

I would have liked to have more practice exercises about tunning.

교육 기관: Yide Z

Dec 13, 2017

good course but there are some small bugs in video and exercises.

교육 기관: Omkar K

Dec 13, 2019

Really good insight into the inner workings of a neural network.

교육 기관: Alexander K

Oct 12, 2019

Too less coding and practice exercises, thou the theory is great

교육 기관: Efthimios K

Jun 13, 2019

Good but need letter recognition NN to understand what he writes

교육 기관: Emanuel G

Nov 08, 2018

Tensorflow part was quite messy, but besides that, very helpful!

교육 기관: Yuki K

May 22, 2018

日本語訳があまりなかったので、英語がそこまで得意ではない初心者の人は勉強の順番の工夫が必要だと思う(自分はそれで乗り切りました)

교육 기관: Junyu Z

Apr 06, 2019

Great course, lecture is perfect. assignments could be improved

교육 기관: wzh

Jan 10, 2019

代码给的答案和自己写代码运行得到的答案不一样,让我想破脑袋想了很久都不知道哪里错了,结果一提交答案评分的时候又说我是对的,头疼

교육 기관: Rory W

May 28, 2018

Good overview of optimization methods, but moves a little slow.

교육 기관: Nicolas L

Jan 25, 2020

programming assignment should be more open, with less guidance

교육 기관: Thomas J D

Nov 08, 2018

Little less well structured/organized than the first course..

교육 기관: Qu S

Oct 27, 2018

感觉讲到tensorflow框架这块儿的时候跳跃有一点点大,如果tensorflow相关的联系更丰富一些,说明更多一些就了

교육 기관: Anirudh

Jun 28, 2018

not very happy about tensor flow introduction. rest was great

교육 기관: Serdar K

Feb 01, 2018

This was helpful. I advise spending more time on tensorflow.

교육 기관: VIGNESHKUMAR R

Oct 23, 2019

Good but need to improve number of examples about tensorflow

교육 기관: Mark

Oct 11, 2018

Good course but a bit more detailed explanations were needed

교육 기관: SANAPALA S

Sep 28, 2017

good but would have been great if tensorflow is covered more

교육 기관: Henry V

Sep 25, 2017

A very good introduction, but a bit basic for professionals.

교육 기관: Ernst H

Jul 07, 2019

Obvious problems. Lessons and quizzes need to be polished.

교육 기관: Nick R

Jan 07, 2018

Necessary background information and how-to for algorithms.