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

RR

Jun 12, 2020

Could have increased assignments and some more indepth knowledge of tensorflow and proper installation way of tensorflow cause mine is showing error when iam trying to practice as shown in the video

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：

6701 - Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization 的 6725 个评论（共 7,286 个）

创建者 Deleted A

•

Apr 17, 2020

Missing the notes in between the videos like in the Intro to Machine Learning course

创建者 Yesid A C M

•

Oct 27, 2019

hay funciones de tensorflow que ser[ia adecuado que las explicaran en los notebooks.

创建者 Asutosh S

•

Jun 12, 2018

Assignments are too easy. They wouldn't even require one to watch the course videos.

创建者 Samit H

•

Jul 14, 2020

Very Good for knowing details . Few more practices in programming might help a lot.

创建者 Cat-zilla

•

Jan 13, 2020

4 stars for the course's rich content. minus one for the overly structured projects

创建者 Deleted A

•

Jan 7, 2020

Excellent course - However, the Tensorflow tutorial could be a little more thorough

创建者 emmanuel m

•

Jan 31, 2021

Wish there was another weeks' worth of learning on tensorflow or more labs for it;

创建者 Gil K

•

Apr 14, 2020

A lot of good topics, but a lot of tasks are irrelevant for todays practical world

创建者 VONGKASEM L

•

Oct 19, 2018

some video lectures have some audio clips repeated, often at the end of the video.

创建者 Bryan L

•

Apr 8, 2018

Good explanation of gradient descent w/ momentum. Nice introduction to TensorFlow.

创建者 Prasanna K

•

Oct 6, 2017

Course content is intense. May be need more detailed videos/lecture on Tensor flow

创建者 Domagoj

•

Dec 11, 2021

Some exercises are not clear enough, that is why 4 stars, overall it is 5 stars.

创建者 Ariel B

•

Dec 16, 2020

Tensorflow 1 assignment should be updated to version 2

Otherwise very good course.

创建者 Krishna T

•

May 11, 2020

Loved the way how Prof.Andrew Ng explained everything in such a simplified manner

创建者 Harsh B K

•

Jul 29, 2019

Good Insights of hyper parameters with other techniques to improve learning rate.

创建者 JETTIBOINA V N D S R P

•

Jul 3, 2019

Content was excellent and it was delivered by Andrew Ng sir in an outstanding way

创建者 NEERAJ T

•

Dec 27, 2018

I thoroughly enjoyed this course. Presents the material in an easy to learn style

创建者 satyasai n

•

Mar 20, 2018

they should have given more lectures on tensor flow but still it is a nice course

创建者 mike b

•

Jan 15, 2021

The assignment teaches tensorflow v1 where I would have expected v2, Keras, etc.

创建者 Bezzecchi E

•

Jan 7, 2021

Good understaning on why certains 'tricks' in nn tuning and regularization work.

创建者 Marwan S

•

Sep 10, 2020

In my opinion,the tensorflow framework should have been set in a separate course

创建者 Martin B

•

Aug 28, 2020

very good but TensorFlow requires more explanations especially in the last block

创建者 Luis E G A

•

Nov 23, 2019

great course, last videos (except for frameworks ) were somewhat hard to follow.

创建者 Ran S

•

May 17, 2019

More excersies on batch norm and hyper parameter search could have been usefull

创建者 成萧何

•

Mar 26, 2019

A programming assignment about batch normalization and softmax will be helpful.