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....



Exceptional Course, the Hyper parameters explanations are excellent every tip and advice provided help me so much to build better models, I also really liked the introduction of Tensor Flow\n\nThanks.


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


5701 - Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization 的 5725 個評論(共 6,425 個)

創建者 Lian L


Great introduction to the tuning options for Neural Networks. Would have loved more visual representations of how different options affects learning and accuracy.

創建者 Wes H


Some oversights in programming assignments and the week by week content is not very balanced in terms of effort/time spent. Otherwise, I would have given 5 stars.

創建者 Julian K


Introduction to tensorflow was kept a bit too short for my taste and the coding part was mainly copy pasting the instruction text from above, making it too easy.

創建者 Harsh R


Best course explains the whole concept in detail and taught by one of the most excellent ML teachers Andrew Ng must to understand the working of Neural Networks

創建者 ShingB


Thanks for providing the coursera for me to learn more about DeepLearning!But the web sometimes cannot open the jupyter, the net work is so unstable to log in .

創建者 Keith S


Great course - Some small typos in the programming exercises and the Tensor video felt a bit rushed (needs 1 more video or lengthier explanations would suffice)

創建者 Thiemo M


A big step forward to understanding how to tune neural network performance. Didn't learn all of this even through a couple of years of trial and error on my own

創建者 KarenMars


This is a very great course about the techniques of optimizing neural networks, for example, I have learned different methods to speed up the training process.

創建者 Israel T C


I suffered too much to handle Tensorflow since it's not well explained for beginners throughout the programming assignment. The rest of the course is awesome.

創建者 irfan s p


good course, but unfortunately different with network and deeplearning course, that has fast response mentor. But all in all the course is full with knowledge

創建者 Kate S


Excellent material! There was one error in the last assignment that cost me a lot of time. Please fix that. Otherwise, very useful programming assignments.



Very Good Course to understand Step by Step

Hyperparameter tuning, Regularization and Optimization to improve Deep Neuaral Networks & Practical Assignments !

創建者 Hanqiu D


Great course and great teacher. The skills in this course is very practical. But I think the assignment should use tensorflow version 2 instead of version 1

創建者 Zach Z


Learned a lot about tuning and different frameworks. Definitely math-intensive and more of a brief overview than a deep dive of these techniques and tools.

創建者 Rekhawar N N


improving Deep Neural networks :Hyperparameter tuning,Regularization and optimization course was amazing! thank you so much coursera and Andrew Ng sir! :))

創建者 Rohan P


Similar focus should be given on programming assignments with a extensive discussion forums. Encourage learners to find functions themselves using google.

創建者 Alex C


Please offer a lecture note in detail instead of just ppt shows for each class video, not to mention that some are missing which is inconvenient to recap.

創建者 Muhammad B A


Great material and lectures. Would've preferred slightly more comprehensive exercises though, and more on tensorflow(any deep learning framework) as well

創建者 Francois-Xavier


The tensorflow programming assignment was a little too easy. It turned out to be more or less of a copy paste work without having to look at the TF docs.

創建者 Masateru H


Great intro to TensorFlow Framework. But the last programming assignment was still giving low percentage accuracy without any notable fault in the code.

創建者 Behrad K H


The content was perfect but last programming assignment was excruciating! But I thank everyone involved in making this course, it was unbelievably good!

創建者 Flaviu I V


I feel like the second course was better then the first one. But there are a couple of typos in some assignments and the assignments are still too easy.

創建者 Mark M


The intro of hyper parameters was from mathematical point of view as good as the basics of week 1, however practical relevance becomes not really clear.

創建者 Stephan W


As always - excellent lectures by Andrew Ng. However, I think that the programming assignments tend to be a it too easy and a bit too much "copy/paste".

創建者 Nitin S


In the last exercise of last week, we have to use TensorFlow v1 which was quite annoying if you already have learned tf v2 other than that great course