Chevron Left
Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization に戻る

deeplearning.ai による Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization の受講者のレビューおよびフィードバック

4.9
60,117件の評価
6,959件のレビュー

コースについて

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....

人気のレビュー

NA
2020年1月13日

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.

AM
2019年10月8日

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

フィルター:

Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization: 151 - 175 / 6,905 レビュー

by Marlon C

2017年9月28日

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!!

by Kyle W

2017年8月15日

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.

by Rohit K

2019年7月6日

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.

by Surya N

2022年1月3日

P​rovides practical insights on ways to go about tuning hyperparameters and techniques to address overfitting, speeding up the training process. Examples and break down of concepts are quite helpful in internalizing different approaches, along with the quizes and assignments. Emphasizes the importance of tooling as well in increasing our productivity, which we seldom find in a typical academic setting.

by Itsido C A

2019年12月16日

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.

by sunshineren

2019年8月31日

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!

by Nouroz R A

2017年9月13日

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.

by ali m

2020年12月28日

It was a joyful experience, I've learned some amazing new ideas like exponentially weighted averages and Adam optimizer. I think Dr. Andrew is an amazing teacher, he teaches us some of his experience in the field so we could explore his way of thinking and learn too much from him. After all this course is very helpful to everyone starting a new journey in The Deep learning world so THANKS A LOT.

by Rohit

2018年7月6日

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.

by XiaoLong L

2017年8月14日

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.

by Anoop P P

2020年6月5日

NIce Course on hyperparameters search and tuning. The optimization functions and its relation to the hyperparameters is well taught. Mini-bacth normalization during training and application of learned parameters in testing is discussed very well. At last, deep learning frameworks were introduced and the practical training on tensorflow framework was awesome. Thaks for the well designed content.

by Ram N

2020年1月1日

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.

by Harry ( D

2018年7月20日

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.

by Mark R

2021年3月22日

Another excellent course. It provides a good background for understanding more about neural networks with a reasonable amount of time and effort. I have no illusion that it is providing knowledge in depth, but I have a much better knowledge of the basic terms and concepts that I did before. I am pleased to know at least something about tensorflow and how to use it to build neural networks.

by Mukund C

2019年10月14日

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.

by Ayush K

2018年6月16日

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.

by colinyu

2018年1月15日

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 .

by shengtian z

2018年3月8日

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!

by Patricio G

2021年10月15日

Comencé esta especialización sin conocimientos de deeplearning en absoluto, hoy habiendo finalizado la especialización tengo una basta noción de este mundo tan apasionante. Quiero destacar la facilidad con la que Andrew transmite su conocimiento, es un instructor de otro mundo!. Feliz de haber realizado la especialización y de continuar por este camino. Gracias a Andrew Ng. y a Coursera.

by Rahul B

2020年9月5日

This has been a very useful course and helps you to understand much more about neural networks including regularization, optimization algorithms, hyper parameter tuning and programming frameworks. The style of teaching and the programming assignments are of a really good standard. The quizes could be improved to be a bit more challenging but they still help to review content quite well.

by Rusty M

2018年12月7日

I learned a lot about the area that is not much talked about in deep learning, which is hyperparameter tuning! The forum was very helpful in debugging the programming assignments! Thank you Prof. Ng for the wonderful course. I thank Coursera as well for believing in me and granting me Financial Aid. It wouldn't have been possible without your help, Coursera Team. THANK YOU VERY MUCH! :D

by Neeraj B

2019年10月2日

This was an excellent follow-up of the first course. Having used adam optimization for almost all the neural network models I have build it was great to understand the mathematical intuition behind adam optimizers. Also the programming assignment gave a wonderful refresher and practice of tensorflow. Overall I'm glad hyperparameter tuning and optimization was chosen as a seperate course

by Manraj S C

2019年10月16日

The course is great and will help you in understanding on how to optimize your deep learning algorithm and tune your hyper-parameters. The course provides insights into the exponentially weighted averages concept too which helps you understand how things work behind the scenes when trying to optimize your algorithm. Dropout and regularization have also been explained to a good extent.

by Chan-Se-Yeun

2018年5月1日

This course is very useful for practical purpose. I've learnt a systematic method to develop and iterate my algorithms, which saves me a lot of time. And it's been the first time that I get to know so many variants of gradient descent method, such as Adam and RMSprop. By the way, the programming assignments get a bit hard, but it help me better understand the algorithms. Thanks a lot!

by Andreea A

2019年2月1日

This was a useful course for newbies in neural networks. It gave useful hints regarding how to update the model one is using based on what problems one observes, as well as how to tune the hyperparameters (if there is enough computational power or one runs a small problem). Obviously, this is just a starting point and one should invest a lot of time and energy to become experienced.