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

52,739 個評分
5,974 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....



Apr 19, 2020

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


Jan 14, 2020

After completion of this course I know which values to look at if my ML model is not performing up to the task. It is a detailed but not too complicated course to understand the parameters used by ML.


351 - Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization 的 375 個評論(共 5,907 個)

創建者 Beltus W N

Jun 02, 2020

The gentle transition from NumPy based implemented deep learning functions to the Google's TensorFlow framework is so smooth and easy to comprehend. My understanding of the concepts has been solidified by the course. Thank you Andrew Ng and the Coursera team.

創建者 Tú A N

Oct 29, 2017

Extremely useful course . I highly recommend it . This course give me some helpful tips to tune hyperparameters , some optimization techniques that never heard before . The intro to Tensorflow in third weed is great . Assignment also proves to be insightful .

創建者 Ka W P N

Apr 07, 2019

The course materials are well-designed. However, I have to say this is not an easy course as I spent a lot of efforts in order to understand how to do the assignments. Overall, I strongly believe the course has taught me what I need to know about this topic!

創建者 Joshua D

May 18, 2020

This was an interesting and challenging course. Andrew gives good intuitions about the fundamentals of improving deep neural networks. I recommend having separate optional sections explaining the math behind some of the concepts for those who are interested

創建者 Jude N R

Nov 02, 2017

This course brought to light a lot of the more intricate topics in deep learning. Compared to my knowledge before the course, I now feel like I have a sound understanding of all the small nuts and bolts that work in a deep learning system. Loved the course.

創建者 Nazmus S E

Apr 18, 2020

This is one of the best courses on Coursera. Cleared a lot of concepts. Before this course, I was always thinking, what to do if I had to classify among multiple classes, but the explanation of softmax was actually very helpful in answering that question.


May 25, 2019

This was a very interesting and different course from others. I found it very helpful

for improving the NNs and the techniques taught with assignments give a well insight so as to how the problem should be dealt with.

Thank you to teachers and to Coursera.

創建者 Vivek V

Nov 06, 2017

A perfect course on Deep learning. Mathematical analysis well put forward by Andrew. I am looking forward to finish Deep Learning specialization. I would appreciate if he provides reference to textbooks to learn more about the fundamentals.

Thank you,


創建者 Jiani S

Jan 04, 2020

Recommend! The parts of batch norm and epoch in mini-batch solved my confusions. And the exercise of Tensorflow is simplify and useful. Without tedious documents, you can easily contruct a neural network for practical problems following the instructions.

創建者 Satyam D

Dec 12, 2018

Yet another great course from Prof. Andrew Ng and Coursera. Deeply grateful to all involved in the preparation of this course. Absolutely essential to learn these concepts if we want to build and optimize deep neural networks for creating great products!

創建者 Kyle L

Dec 23, 2017

The conciseness of the course material and interviews with industry experts offer thorough insight and can inspire confidence in new and old DNN learners alike. I look forward to learning more in the remaining courses of the Deep Learning Specialization!

創建者 Naman S

Jul 23, 2020

As expected from and Sir Andrew Ng, this course was really great!

Choosing between so many hyper-parameters and tuning them can be a confusing task, but this course explains each one in detail and simply.

Thank you for this amazing course!

創建者 Camilo M

Jun 23, 2020

Not long ago I have been working with machine learning and artificial networks, but without a doubt so far I think my learning curve has been exponential. Themed content is for anyone to fall in love with technology and climb on the shoulders of giants.

創建者 Akash R

Dec 16, 2018

I understood the bits and pieces of how tuning particular hyperparameters will lead to a great improvement model being developed. Andrew NG was great to teach everything with examples and deep dive into the concepts. Thanks for the opportunity provided.

創建者 Ravi B

Dec 19, 2017

Great course on practical techniques to tune hyper parameters. Great to see the practical experience driven lectures with succinct, focussed theory. Learning has never been so exciting. Kudos for the team who put together such as great code scaffolding.

創建者 Keith T

Oct 28, 2017

Andrew Ng picks up where he left off with 'Machine Learning' and takes a relatively complicated subject and breaks it down into clear an understandable blocks, providing insight and intuition along the way. But that's what great teachers do well, right?

創建者 Myunggwan C

Feb 17, 2019

I'm on the road to improvement with my deep learning skills with the current specialization.

Thank you for providing such a great quality course online.

I also appreciate the mentors who comment to every post in discussion group.

Keep up the good work!


Nov 13, 2017

Very wonderful and thought provoking stuff has been provided for learning optimization and regularization. Latest stuff have been used to demonstrate the examples. Thanks to Coursera for providing a good platform to learn all this tools and techniques.

創建者 govind b

May 09, 2020

This course is good for those who want to learnt about the different regularization technique and the most important optimizer algorithms. The course material is good and easy to understand. I liked this course so much and it teach me lots of things.

創建者 J.-F. R

Feb 18, 2020

Great course by Prof Ng. I had taken his Machine Learning course a few years ago, so expected high standards of content and assignment preparation - I was not disappointed. Staff is very responsive and helpful in forums as well. I highly recommend it.

創建者 Rohit G

Sep 18, 2017

In-depth learning about Hyper-parameter Tuning, multiple Regularization and Optimization Techniques. This Course makes learning Deep Learning Framework like Tensorflow very easy.

All thanks to Andrew NG and team for building this course so interactive.

創建者 Nikesh P

Jan 23, 2019

Hyperparameters can affect our parameters and how tuning them properly would speed up our optimization is nicely taught. And it was great to know the intuition and mathematics behind other optimization algorithmswhich which was also taught very well.

創建者 Monil J

Jun 10, 2020

It's been a great learning through out this course. Even by improving hyperparameters, tuning them and optimizing them, we can increase the efficiency and reduce the execution time very much.

Thank you so much Andrew Ng sir for this amazing course!!!

創建者 Victor

Jan 16, 2020

This course is very useful, a good extension of the first deep learning course. Like the name of the course, on top of the basic neural networks knowledge, this course focus on how to improve the performance of the fundamental neural networks built.

創建者 Navy X

Sep 25, 2017

In the course there are lots of impressed optimization strategies that are hard to get outside from here. I was shocked when I saw the performance improvement after I run He initialization and Adam, according to the instruction in the course. Great!