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

4.9

40,746개의 평가

•

4,339개의 리뷰

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....

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

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:

교육 기관: Sachin P B

•Mar 05, 2019

Found it so helpful! Truly among the best!

교육 기관: Ethan ( W

•Mar 05, 2019

Great intuition to understand how to improve deep learning

교육 기관: ABHINAV S

•Mar 05, 2019

It is a great course. The concepts for hyperparameter optimization are explained in best and intuitive way. Also math is really made easy for better understanding.

교육 기관: Jitin K

•Mar 06, 2019

Prof. Ng is a great instructor. The course is very well structured and broken down into easily digestible materials. Very useful for a ML/Deep Learning Student.

교육 기관: Ishaan Y

•Mar 06, 2019

very nice course i loved it :)

교육 기관: Jimut B P

•Feb 28, 2019

Just awesome course! Never learned so well before.

교육 기관: 荣灿

•Feb 28, 2019

excellent!

교육 기관: Vishnu N S

•Feb 28, 2019

Great Work !!!!

교육 기관: Julian L

•Mar 03, 2019

Muy bueno en la forma que se explica los conceptos. Gracias

교육 기관: Camilo G

•Mar 02, 2019

Great way to introduce topics in Deep Learning

교육 기관: SURAJ K

•Mar 02, 2019

This course really nailed down to tuning process and I would totally recommend to everyone especially if you are interested in doing ML using Python.

교육 기관: Anurag V

•Mar 03, 2019

Andrew NG is awesome...

교육 기관: ENRIQUE A C A

•Mar 04, 2019

Excellent course

교육 기관: Vitalii S

•Mar 03, 2019

Easy, thanks for good suggestions and interesting information.

교육 기관: Pradeep I

•Mar 04, 2019

What learned during the course was building the self confidence in the subject area really lot.

교육 기관: sai p j

•Mar 03, 2019

Great course on Deep Learning. Thank you very much Andrew NG and Coursera.

교육 기관: Dupuy N

•Mar 03, 2019

Very nice methodological lesson on deep learning

교육 기관: Prabesh G

•Mar 05, 2019

Simply the best

교육 기관: GEORGE A

•Mar 05, 2019

Pretty solid class, learned a lot of basic concepts. The class won't go into a lot of mathematical details about the algorithms however, there is enough intuition provided in order to understand the inner workings of the algorithms and the logic behind them. The only con I have is that some of the programming exercises look outdated with the current versions of the notebook. For example, in my last exercise I couldn't make the NN with tensorflow to work properly but got 100/100 nevertheless.

교육 기관: Hyeon S J

•Mar 05, 2019

Very Nice!

교육 기관: 나종호

•Mar 04, 2019

thank you so much.

교육 기관: mprc_liu

•Mar 04, 2019

very very good

교육 기관: BEDOURET

•Mar 04, 2019

Super !

교육 기관: Yuan L

•Mar 04, 2019

very practical and well organised course

교육 기관: Alexey D

•Mar 04, 2019

Great structured course which helped me a lot with understanding of the main aspects of how Neural Networks do what they do, and how to make them predict better.