返回到 Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization

4.9

星

43,945 個評分

•

4,776 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....

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.

Oct 09, 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

篩選依據：

創建者 David R R

•Nov 15, 2017

This course gives you a better understanding of how to increase the performance of your neural network.

There are some video-lectures that are a little harder to understand and maybe boring but, in general, I recomend this course.

Este curso te da un mejor entendimiento de como aumentar el rendimiento de tu red neuronal.

Hay algunos videos que son dificiles de seguir y quizas aburridos pero en general recomiendo hacer este curso.

創建者 Sikang B

•Apr 01, 2018

Clear and practical, this course sets a good bridge from the old NP based programming model to the modern programming models of using Tensorflow and Keras. The optimization methodologies lead to the very useful aspect of ML: hyper-parameters tuning. Though a lot of these hyper-parameters still feel magical, it is super helpful to know more about them.

Suggest to clearly mark this course as a requirement for course 4 and 5.

創建者 Durgaprasad

•Jan 20, 2020

This course builds upon the fundamentals learnt in the first course. By doing this course I have learnt the importance of regularization, and initialization of weights while training a neural network. The course also gives information on implementing neural networks on large datasets and how to methodically choose the hyperparameters. The course exercises are informative and helped me in solidifying the theory learnt.

創建者 David S B

•Jul 24, 2019

Excellent course - my only complaint is that the grader is really finicky about completing the notebooks in a very specific way. Your submissions get rejected in a very cryptic way if you use certain valid TensorFlow constructions, namely you cannot use "Z = W @ X + b", instead you must type "Z = tf.add(tf.matmul(W, X), b)", which I find much more difficult to read. Nonetheless, I think this was an excellent course.

創建者 Heinz D

•Nov 06, 2019

Great course, great instructor and staff. Good speed and good hands-on exercises. Some flaws in the downloadable material and a couple of everlasting corrigenda, but nothing too serious. Integrity control could be enhanced in the TensowFlow assignment. I wish there were not only quizzes at the ends of the weeks but also inbetween or even within the lectures. Looking forward to the next course in this specialization.

創建者 Jaime M M

•May 29, 2019

Very good course as well, although the exercises need some "debugging" there are some typos and errors. I found that the previous courses exercises where too guided, too easy in some points. In this case are more tricky, but not in the correct sense. I would orient a bit more the way of thinking or refer to external sources to get a bit more on track with TF before coding. Nonetheless, all in all, is a great course.

創建者 Renzo B

•Aug 28, 2019

It was a very insightful course. I learned the basic intuition behind the concepts that Andrew Ng explained. For my suggestions, maybe the deeper derivations and meanings behind the concepts could be discussed in video or just a reading material. For example with the maths behind regularization, batch normalization and etc. could be discussed more in depth in a reading material. All in all the course was excellent.

創建者 Mehedi H

•Sep 24, 2017

Very good one. It was great pleasure to learn momentum , RMSProp and then coming to know how to combine them in Adam. Tensorflow example was great. In tensorflow exercise, using regularization can give a boost in the generalization of data which has been mentioned (and I tested it )-but this could have been a part of the exercise.

However, starting to audit the next course of this series. Best of Luck for me !! :D

創建者 Mikhail G

•Mar 07, 2020

Very nice course, worth taking for everyone who is interested in ML/Deep learning, including the very beginners and professionals. I work at the edge of Neuroscience/ML/AI, I have a strong theoretical ML background, but little practice. Even though I was familiar with many of the concepts before taking the course, it was still extremely useful to hear about it again and have way better understanding of the topic

創建者 Lyle T

•Sep 15, 2017

Very good in-depth coverage of mini-batch, ReLU, Adam, L2 and dropout regularization. Good overview of batch normalization. Brief but useful intro to Tensor Flow (including programming assignment). In general, the programming assignments are pretty easy, but a bit hard to debug in the Jupiter notebooks, though I was able to get things working by inspecting the code to locate typos.

Summary: Highly recommended

創建者 Jingyu Z

•Jul 15, 2019

This Course is really good for the beginner of NN and deep learning. It tells me what to consider and how to consider for model build-up. I also like the quiz which helps me to check my concepts understanding, the coding practice is easy to understand and I can logically learn how to practice my understanding of this session. I also love the interview session with DL Heroes. This course is really inspiring.

創建者 Marlon A C V

•Sep 28, 2017

This course is AWESOME, a lot of new things related to Deep neural networks regularization techniques, initialization techniques and Tensorflow Neural Networks modeling. A step forward into mastering applied Artificial Neural Networks!! Course really recommended for ML/AI enthusiasts and begginer or promising researchers in the field. I recommend to take all the courses provided in this DL Specialization!!

創建者 Kyle W

•Aug 15, 2017

Great course. I'm particularly happy that they chose to teach TensorFlow. There were a number of typos/errata, which is to be expected with such a new course, but it looks like they are working quickly to address them. Overall, I feel more confident implementing neural nets than I did after the original ML course taught by Andrew Ng.

Watching Andrew try to draw a horse in one a the lectures is a huge bonus.

創建者 Rohit K

•Jul 06, 2019

Hello Andrew, I am a big fan of you. Learning from your every course. Very unfortunate that I can do that remotely only.

One thing that I want to mention - Can we have lecture notes on coursera, just like the way used to in CS229 that we can read before coming to next lecture. I found that that was very useful in understanding when things get harder.

Thanks hope we can improve coursera in that matter.

創建者 Itsido C A

•Dec 17, 2019

This is a must to really understand and master the art of machine learning. With this course I understood that building a model and training it is not even half of the story of being a machine learning engineer, without knowledge of how to tune the models parameters you might not be able to deliver product on schedule. Thanks for Dr Andrew and the team for an awesome content and learning experience.

創建者 sunshineren

•Aug 31, 2019

It is really a EXTREMELY GOOD course for a bad-basic student, according this course, not only I have know the theories, but also the pratical project.I do think now I know the BN, the Hyperparameter, and the Regularization and so on in Deep Learning field! It would be very helpful for me to step into the AI!

and both videos and lectures are very important for new comers in deep learning ! THANKS ALOT!

創建者 Nouroz R A

•Sep 13, 2017

This is one of the best MOOC I have ever come up to. Very informative, well explained and easily put. This course helped me to learn so many new things that I had missed in books and research papers. Thanks Andrew Ng, this was like a debt to me. As a wannabe deep learning researcher/Engineer, your contribution to help me catch the basic concepts will always be remembered. :-)

Yes, highly recommended.

創建者 Rohit

•Jul 06, 2018

This course has really helped me alot in gaining better insights about improving deep neural networks by tuning the required hyperparameters. It has also increased my understanding of the previous course and I would definitely recommend this course. I would like to express my gratitude from the bottom of my heart to the Coursera team and the specialization course team for such an amazing course.

創建者 XiaoLong L

•Aug 14, 2017

After reading the Deep Learning book wrote by Ian Goodfellow, it's much more easy for me to complete this course within two days. I've gotten a lot through this course and know more detail about the deep learning hyperparameter tuning, regularization and optimization methods now. Thanks so much for Prof. Andrew and TAs. I will keep learning the 3rd course in this specification of deep learning.

創建者 Ram N

•Jan 01, 2020

The course covers the theory and implementation details of advanced optimization algorithms. A good amount of intuition was provided in the explanation of these algorithms. A basic explanation of bias and variance and how hyper parameters affect them both is explained clearly. I liked the hands on part, as it allowed me to implement the algorithms discussed and gain more clarity in the process.

創建者 Harry ( D

•Jul 21, 2018

Very useful follow up to the first course in this specialization. Learned all the details of how to tune and optimize a deep neural network, as well as nice introduction to Tensorflow. Some typos in the comments of the final assignments but they were easy to spot. This time Jupiter notebooks worked better that during the time I was working on the previous course with less or no resets required.

創建者 Mukund C

•Oct 15, 2019

Excellent Course. Really structured way of learning the importance of hyper parameters and their effects on the learning/training and hammering concepts like "regularization" home.

Just an observations, but it seems like the mentors are not that engaged in these courses anymore, but there are enough help threads that one can figure out the questions - specifically on the programming exercises.

創建者 Ayush K

•Jun 16, 2018

What an amazing course it is. Perfect explanation how we can use optimize our cost more efficiently and effectively. Also this course includes techniques to overcome problems like over fitting i.e Regularization and Dropout techniques. Information about Batch Normalization is very splendid. Also got little intuition about tensor flow. Thank You Andrew Ng for providing such a wonderful course.

創建者 colinyu

•Jan 15, 2018

Prof Ng is a great teacher and is good at making the difficult material very easy to learn. I am very interested in the DL. Before I took this class, I found that since this field is very new so all the material you can find is a little piece and not systematical. This specialization is a wonderful and systematical, easy to learn and fun. Thanks for the great work those teacher have done .

創建者 Zhou S

•Mar 08, 2018

Awesome illustration on deep network's regularization techniques, weight initialization techniques and gradient checking, and more. This class provides you with hands-on experience with how to tune a deep network efficiently. You will not only learn the techniques but also understand many of the intuitions of how each technique works. A must take if you are dedicated into machine learning!