Chevron Left
返回到 Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization

学生对 DeepLearning.AI 提供的 Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization 的评价和反馈

4.9
星
63,507 个评分

课程概述

In the second course of the Deep Learning Specialization, you will open the deep learning black box to understand the processes that drive performance and generate good results systematically. By the end, you will learn the best practices to train and develop test sets and analyze bias/variance for building deep learning applications; be able to use standard neural network techniques such as initialization, L2 and dropout regularization, hyperparameter tuning, batch normalization, and gradient checking; implement and apply a variety of optimization algorithms, such as mini-batch gradient descent, Momentum, RMSprop and Adam, and check for their convergence; and implement a neural network in TensorFlow. The Deep Learning Specialization is our foundational program that will help you understand the capabilities, challenges, and consequences of deep learning and prepare you to participate in the development of leading-edge AI technology. It provides a pathway for you to gain the knowledge and skills to apply machine learning to your work, level up your technical career, and take the definitive step in the world of AI....

热门审阅

BA

May 31, 2020

Very good course, useful and smart. Some of the example are on tensorflow 1 but I think that they will update them soon to keras tf2 Thank you!I will pass on what I have learned here to undergrads :)

DH

Apr 26, 2020

Everything, Everyparameter in neural networks looks familiar to me now. I feel like I can optimize them for better accuracy. Overall I learned some new things and the way of teaching was really nice.

筛选依据：

3351 - Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization 的 3375 个评论（共 7,286 个）

创建者 Fernando E L M

•

Oct 17, 2018

Excellent training, easy to follow material and labs.

创建者 Muhammad R M

•

Oct 9, 2018

This course is a little tough but Its really worth it

创建者 Future H

•

Aug 24, 2018

Excellent explanations by Dr. Ng, easy to understand.

创建者 Wang J

•

Jun 23, 2018

Andrew Ng is one of the best teacher I have ever met.

创建者 Yu Q

•

Apr 20, 2018

A little hard to learn but very practical and useful!

创建者 Jagadish K J

•

Apr 17, 2018

Very Important course to learn Hyper parameter tuning

创建者 Yash N

•

Mar 9, 2018

The best resource on Neural Networks on the internet!

创建者 Wynand

•

Feb 21, 2018

Andrew is great at breaking AI down into simple steps

创建者 LakshmiNarayana B

•

Feb 7, 2018

Very helpful in understanding ways to optimize models

创建者 Matt S

•

Dec 27, 2017

It's great for the practice of projects in real work!

创建者 Shubhadeep R

•

Nov 30, 2017

Learned a lot from this course. Thank you Andrew Sir.

创建者 郭建隆

•

Nov 27, 2017

Andrew is a really great teacher that I've ever seen!

创建者 Pankaj D

•

Nov 27, 2017

As always a wonderful course from an amazing teacher!

创建者 Gregorio A A P

•

Oct 17, 2017

EXCELLENT COURSE, BUT LACK OF TRANSLATION IN SPANISH.

创建者 pablo s

•

Sep 22, 2017

Very thorough and detailed explanations, very useful.

创建者 PeiSheng S

•

Sep 13, 2017

Very helpful, it really taught me many useful skills.

创建者 Mar G

•

Nov 23, 2023

Amazing, I am learning a lot and having so much fun!

创建者 JAGDISH R

•

Jan 21, 2022

For a student this course is certainly a blessing :)

创建者 Sina B

•

Sep 10, 2021

I mean it's Andrew Ng! That's all you need to know!

创建者 Bharath D

•

Jul 21, 2021

Very Nice Course for learning basic of Deep Learning

创建者 Charles X

•

Jun 12, 2021

Very good course, contents useful in real practices.

创建者 Kunwar P

•

Feb 6, 2021

Thanks to Dr. Andrew Ng and the whole Coursera team.

创建者 Diego G A

•

Sep 11, 2020

Excelente curso!

Lo recomiendo con los ojos cerrados.

创建者 Luis E O P

•

Jul 5, 2020

Excelente curso, excelente profesor, muchas gracias.

创建者 Koushik G

•

Jun 29, 2020

Very Structured way of deciphering complex concepts.