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
63,489 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

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.

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

筛选依据：

6601 - Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization 的 6625 个评论（共 7,283 个）

创建者 Alex S

•

Dec 11, 2018

A small validation output error that is still not fixed prevent to rate all stars for the exellent course.

创建者 苑思域

•

Aug 3, 2018

This one is actually a little bit better than the first one, maybe less content, maybe more understandable

创建者 Leitner C S E S

•

Aug 29, 2017

Excellent course. But -1 for using TensorFlow, a not-really-free framework, to introduce students to them.

创建者 Jayshree R

•

Jul 4, 2019

An intuitive approach towards Hyper parameters. Covers the concept of optimization algorithms quiet well.

创建者 Makragić A

•

Jan 9, 2019

Great lectures, I'm little disappointed with TensorFlow tutorial, there should be 1 week for that only...

创建者 Richard H

•

Sep 28, 2017

Fills in the tricky gaps in using DNN that are necessary to transition from basics to practical projects.

创建者 Harry L

•

Mar 21, 2020

Too much code is given, which makes the programming assignments too easy. The material is great, though.

创建者 Shijian G

•

Nov 28, 2019

These series are generally clear and well-organized. It would be better to provide tensorflow materials.

创建者 Kevin T

•

Mar 29, 2023

The assignments could have been explained a little bit better. The course was overall very interesting.

创建者 Joseph A

•

Dec 6, 2020

The course was very great, although I feel I needed a better explanation about tensorflow functionality

创建者 Tien N V

•

Jun 24, 2020

This course so very good for person who wants to understand the optimization topic in machine learning.

创建者 Tanmay

•

Jun 1, 2020

Nice content; creators must try to focus on enhancing the confidence of learners to code by themselves.

创建者 Ranjan D

•

Jul 17, 2019

Great explanation on tuning different hyper parameters and how they can effect the model's performance.

创建者 Keanu T

•

Jun 25, 2019

I wish it went a little more in-depth with softmax classifiers but I can find that online so it's good.

创建者 Byron M

•

Apr 8, 2018

The final assignment didn't have the right instructions, a lot of misleading comments and instructions.

创建者 Matías L M

•

Oct 29, 2017

The professor is really good at explaining. The projects got more interesting than in the first course.

创建者 Per K

•

Oct 2, 2017

Get you to a more practical understanding of deep learning. The introduction to TensorFlow is valuable.

创建者 Alexander

•

Mar 9, 2020

I would like to learn the V2 of TensorFlow. Except that. exceptional course. I love Andrew's teaching!

创建者 LEO L

•

Jul 30, 2019

All is good except the submission part, sometime return submission failure without specifying a reason

创建者 Deleted A

•

Jun 22, 2019

Great Course ! I learned a lot, but I would have preferred another Framework though (like Pytorch) ...

创建者 Qingyun W

•

Jun 6, 2019

Some typos in the programming assignment is still not fixed (Mentioned in top posts in the discussion)

创建者 Ryan M

•

Oct 7, 2018

a very informative course, I was introduced to Tensorflow through this course... I absolutely loved it

创建者 Dan C

•

Feb 28, 2018

I had a bug in my compute_cost function that caused cost to spiral but the grader did not catch it....

创建者 Yash J

•

May 17, 2020

There should have been deeper explanation for the tensor flow section. Otherwise an excellent course.