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

學生對 提供的 Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization 的評價和反饋

56,647 個評分
6,498 條評論


This course will teach you the "magic" of getting deep learning to work well. Rather than the deep learning process being a black box, you will understand what drives performance, and be able to more systematically get good results. You will also learn TensorFlow. After 3 weeks, you will: - Understand industry best-practices for building deep learning applications. - Be able to effectively use the common neural network "tricks", including initialization, L2 and dropout regularization, Batch normalization, gradient checking, - Be able to implement and apply a variety of optimization algorithms, such as mini-batch gradient descent, Momentum, RMSprop and Adam, and check for their convergence. - Understand new best-practices for the deep learning era of how to set up train/dev/test sets and analyze bias/variance - Be able to implement a neural network in TensorFlow. This is the second course of the Deep Learning Specialization....



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


Very good course to give you deep insight about how to enhance your algorithm and neural network and improve its accuracy. Also teaches you Tensorflow. Highly recommend especially after the 1st course


5776 - Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization 的 5800 個評論(共 6,430 個)

創建者 Swann C


Good material and definitely essential in order to gain a lot of time aiming at the right direction navigating all these parameters

創建者 Amine D


Very good course. I would have liked a little longer introduction to the tensorflow architecture and less help on the assignements

創建者 Stanley C D


A good introduction to gradient descent algorithms and hyperparameter tuning with a little TensorFlow thrown in for good measure!

創建者 Jorge


Good course, Hyperparameter tuning, Regularization and Optimization are well explained, and the Tensor Flow lab is very useful too

創建者 Marcela I


Es un buen curso, basado principalmente en aspectos prácticos. Me pareció menos interesante que otros de la misma especialización

創建者 Xin X


Tips are very useful! Have some typos/errors in assignments, more coding work can help understanding. Thanks for sharing, Andrew!



Many practical tricks such as tuning hyper parameters and the use of major optimization techniques such as batchnorm and dropout.

創建者 Md. T R


I think a bit more hands on teaching would be better for this course and also if you could mention resources it would be better.

創建者 Victor-Hugo J


Very interesting course. But a bit fast I would say. Sometimes I didn't feel the programming assignments were that challenging.

創建者 kevin k


The course was great overall, but I wish we had more involvement in the set up of the programs in the programming assingments.



It would've been much easier if the graded functions of the tensorflow practice assignment would've been explained separately.

創建者 Dário P


Nice basics that help understand the fundamentals. The last part of the course should be upgraded to Tensorflow 2.0 already...

創建者 Uddhav D


Again awesome explaining by Andrew, although I feel Batch Normalization should be a bit stressed upon and explained in detail.

創建者 Tarun S


Well detailed course..

Tensorflow is very basic and it could have been improved if one can visualize graphs too in tensorboard

創建者 Pranay V


Explains neural nets like a tutorial more than a formal course. Overall pretty insightful. Also, instructor can speak louder.

創建者 Steven A


Great course!! The only improvements I'd suggest is more difficult assignments (less guided) and more written documentation.

創建者 Shashank K


Some of the best intuitions behind Neural Networks can be provided by none other than Andrew Ng and this course proves that!

創建者 Kevin M


Very good - wouldve been more effective if included the questions part way through the videos as previous courses have done.

創建者 Jonathan G


Es necesario que actualicen los notebook por ejemplo el de TensoFlow ya que esos códigos no corren bien con la nueva versión

創建者 Alonso O O


This course was a little bored for me. I already knew a little bit about hypertuning so I felt that the course moved slowly.

創建者 Omar S


Provides a good code skeleton to build a neural network, but would unlikely have one poised to do improvements on their own.

創建者 Kevin C


Está bueno el curso pero quizás lo más interesante sea el uso de TensorFlow al final para que todo empiece a tener sentido.

創建者 Om S P


Some assignments, even though I get the same result as the output given, it get marked as wrong... Please try to rectify it

創建者 Victor P


Very good course from the excellent Andrew Ng.

Some typos and some glitches in the video, hopefully it will improve in time.

創建者 Alex N


Good pace

Only drawback is that some of the safe checks are wrong in the programming assignments, even with the right seeds.