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
63,491 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

AA

Oct 22, 2017

Assignment in week 2 could not tell the difference between 'a-=b' and 'a=a-b' and marked the former as incorrect even though they are the same and gave the same output. Other than that, a great course

筛选依据:

626 - Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization 的 650 个评论(共 7,283 个)

创建者 Vengatramanan R

Jun 10, 2018

Thanks to Andrew and his team. The materials were easy to understand and the assignments helped gain confidence. My suggestion is to remove the 'fill in the blanks' type assignments and make it little more challenging.

创建者 JONNAKUTI P K R

Jun 28, 2022

Thank you Prof. Andrew Ng for such a wonderful course and getting me interested in Deep Learning domain! The concepts were explained in a simple and most-intuitive way! Love the explanations of concepts in the course!

创建者 Avinash

Aug 18, 2020

I feel that programming exercise of the last week of this course does not cover full of the third week videos.The concepts like batch normalization, hyper-parameter tuning. Other than that this course is very helpful.

创建者 Dr. S V

Apr 27, 2020

This course is excellent, I understand all the hyper parameters and underlying concepts in tuning them to optimize Deep Neural networks. The introduction to tensor-flow and practical session on it is very much useful.

创建者 Michalis P

Oct 11, 2019

Another great course, for getting your hands dirty with deep learning. Gained enough intuition about topics related with hyper-parameter tuning and learned about several optimization algorithms. Thanks for this course

创建者 Nikhil V K

Oct 9, 2019

Enjoyed the course and programming assignments alot. Gained knowledge regarding Adam Optimization and batch normalization and learnt how to implement neural network in tensorflow. Teaching by Andrew Ng sir is awesome.

创建者 Mallikarjun C

Feb 7, 2019

Excellent Practical advice on Improving Deep Neural Networks, Interesting talk with Heros of Deep Learning: Yoshua Bengio and Yuanging Lin and good programming exercises including nice introduction to using TensorFlow

创建者 Danush V

Jul 30, 2018

Another masterclass from Dr. Andrew on Deep Learning. This course helps us in building a perspective on identifying significant hyper parameters influencing the performance of Neural Networks and how we can tune them.

创建者 Zhuoqing F

Jul 22, 2018

I'm a biologist. This course explains basic component of deep neural networks, and it is the most clearly explained course I've even taken. Through this course, I could implement deep neural network even with numpy !

创建者 Gowtham B

Mar 11, 2018

Andrew's explanation is so crystal clear that it makes us program the most difficult aspects of Deep Learning to work on smoothly and easily with great clarity. It is a great experience always to learn from Andrew Ng.

创建者 Pavel C

Sep 26, 2017

I've came to this course specially to clarify hyperparameters and optimization algorithms. But decided to start from course 1 in order not to miss anything important.

I've got answers I was looking for! Thanks a lot!

创建者 Albert M

Feb 27, 2018

Enterteining and insightful approach to DL. I find the programming assignments very useful, hands on practice. I feel that I am capable of implementing almost from scratch a real DL NN and I cant test it performance.

创建者 Tian Q

Dec 26, 2018

Excellent course. Andrew balances theory and intuition perfectly when explaining a method or an algorithm. He helps me to see not only why something is mathmetically correct, but also why it makes sense intuitively.

创建者 Waseem

Dec 7, 2018

This course had cool insights into the workings of various optimization algorithms. It has definitely helped me go beyond the black-box understanding of Adams Optimizer / RMSProp / Momentum etc.

Highly recommended !

创建者 Vijay A

Dec 13, 2017

Even though setting up Neural Networks is easy, making them work according to our need requires a lot

of knowledge and practice.We get exposed to many such practices in this course.It was a great learning experience.

创建者 Avinash K

Nov 1, 2017

This is really good course. I have already learnt most of the topics through different books so I could complete the course very fast. Tensor flow is a very important tool and its inclusion in this course is a plus.

创建者 Alan H

May 11, 2020

this course does a great job explaining concepts and providing guidance in the assignments. I sometimes wish they provided less scaffolding, but my assignments in this course will be a useful resource going forward

创建者 Mashrukh Z

May 10, 2020

This course really helped me with some terms like L2 regularization, Dropout, Adam Optimization and finally implementing the whole idea on Tensorflow. Thanks a lot to Andrew and his associates! I loved this course.

创建者 Asif A

May 8, 2020

I recommend this course to all the professionals who are working in market of deep learning & machine learning. This course will equip you with all types of necessary skills to cope with real world ML/DL challenges

创建者 Saif N

Feb 10, 2020

This course introduces the basic and key concepts of neural networks which are essential in building deep neural networks based on their problem application. I loved how TensorFlow has been introduced with exercise

创建者 Jonathan S

Jan 18, 2018

Not bad, but I felt the exercises had maybe a touch too much hand holding, and he never talked about how to compute the derivatives of Adam Optimization, though of course we promptly use Tensorflow to do it for us.

创建者 Giovani F M

May 30, 2020

Excellent course to learn about Hyperparameter tuning, Regularization and Optimization. The concepts are well explained in an intuitive way. The programming assignments are really useful to apply what was learned.

创建者 Debashish N

Jun 20, 2019

I personally feel that this is one of the most important courses included in this specialization as it helps us tune our model to the best possible parameters. Don't skip this course at any cost, dear colleagues!!

创建者 Aniruddha S H

Mar 19, 2019

this was amazing. Explained almost all the hyperparameters, why we need those and how can we optimizat those. along with regularization, dropouts. Everything was explained from need to the hands on implementation.

创建者 Moses W W

Jan 2, 2018

This is an awesome Deep Learning training course, Prof Ng depict all the key and hardest part of deep learning in this one single online course, which is still a mysteries for many people without going through it.