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
63,478 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

AM

Oct 8, 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

DD

Mar 28, 2020

I have done two courses under Andrew ng and I am grateful to Coursera for their highly optimised and easily learning course structure. It has greatly help me gain confidence in this field. Thank you.

筛选依据:

7251 - Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization 的 7275 个评论(共 7,283 个)

创建者 Cristian G

Sep 28, 2022

They should improve the programming labs.

There's too much repetition in things like programming a function that initializes the parameters while important things, like model definition, are already written in the notebook.

创建者 James H

Nov 18, 2018

The whole tensor flow introduction is weak - it clearly requires further reading, which is fine but totally out of kilter with the videos so far, which have taken things from first principles very clearly.

创建者 Martin B

Nov 16, 2017

A technical problem with the grader caused my grade to be artificially lower on the last project. Although I was instructed to resubmit, the course ended with a lower grade than I should have received.

创建者 Anne R

Oct 9, 2019

Not much implementation required of the students. More testing of the methods would be useful or if the concepts are the focus then this course should be merged into another course in the sequence.

创建者 Brian R

Jun 10, 2018

The course material is good but Jupyter notebook interface does not work correctly. You will waste a lot of you precious time fiddling and redoing work that you lose when the notebook fails to save.

创建者 Abhishek K

Dec 20, 2019

could be accomplished in a week. wastes time and doesnt go in sufficient depth.

After completion, you will get a 'taste' of optimization techniques, but it is not way comprehensive.

创建者 Don F

Feb 1, 2018

The course was good but there were multiple mistakes in the final programming assignment. These mistakes were reported in the forums over 4 months ago and have not been addressed.

创建者 Sam G

Mar 12, 2020

I find that the programming assignments have a LOT of copy pasta. Also, wasn't enthused to hear that we are using an out of data framework.

创建者 Jaime T G

Jan 22, 2019

Very poor explanations, not correlated with the quitz and exercises. Missing more theoretical material in pdf with some more explanations.

创建者 Harshit G

Feb 7, 2020

the instructor must give some more detailed explanation of the optimization techniques and hyperparameter tuning

创建者 Deleted A

Sep 30, 2017

From my point of view this course deserves a bit more time. Too much material rushed through in too little time.

创建者 Antoine J

Apr 11, 2020

Was way harder than the Course1 and Course2. Should be simplifier on topic la batch norm, expo. weighted avg..

创建者 Nathen N

Sep 13, 2020

The notebooks of this class are terrible. They should receive more attention so you actually learn something.

创建者 Sanford F

Jan 24, 2019

There are many errors in the course materials and no one seems willing to fix them.

创建者 Jay L

Mar 25, 2021

When I submit the assignment, the output is the same, but there is no point for it

创建者 Daniel T

Sep 21, 2017

The programming assignment for week 3 was full of bugs

创建者 Shankar N

Feb 17, 2019

Could have been a 4 week course

创建者 ENDER D I

Aug 22, 2021

last pa needs revision

创建者 Rahul K

Apr 4, 2020

very basic course

创建者 Alex M

Jun 12, 2020

ala0z

创建者 Ahmed N

Aug 21, 2023

good

创建者 zl 大

Apr 14, 2022

here is a bug in Week1's programming assignment,Gradient Checking ("Exercise 3 - gradient_check" and "Exercise 4 - gradient_check_n")

the problem is that I search everywhere in forum provided by the course and still cant find a solution,none of course's administrator or man in charge provided a solution,instead of they told you over and over again"make your question on Deeplearning.AI",which is their community forum

I just ask for a solution ok so i can fix this assignment and pass

"

创建者 Anders B

May 23, 2021

The course was updated half way through, we were automatically rolled on to the updated version and progress already made on the course was reset from under our feet. We had to retake previously completed and passed content, wasting much time. It also did not help that the website reported the course content we had to retake as complete in some areas of the site and not others.

创建者 Rohan K

Feb 26, 2020

i am doing course in feb and i have been assigned sessions in april. Cant view even assignments or programming assignments before April. Totaly rubbish

创建者 Sean L

Sep 9, 2019

Love the content but unable to reset course when deadlines pass is VERY ANNOYING.