Chevron Left
Back to Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization

Learner Reviews & Feedback for Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization by DeepLearning.AI

4.9
stars
63,068 ratings

About the Course

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....

Top reviews

YL

Invalid date

very useful course, especially the last tensorflow assignment. the only reason i gave 4 stars is due to the lack of practice on batchnorm, which i believe is one of the most usefule techniques lately.

NC

Invalid date

Yet another excellent course by Professor Ng! Really helped me gain a detailed understanding of optimization techniques such as RMSprop and Adam, as well as the inner workings of batch normalization.

Filter by:

926 - 950 of 7,238 Reviews for Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization

By Jagrati S

Mar 22, 2020

For a busy mom of 2, 42 year old, senior executive., this course is best optimize for the pockets of time I get. Concepts are explained very clearly, and course is well paced

By Antonio G

Jan 28, 2019

It couldn't be better, thank you very much and greetings from Ensenada B.C. Mexico.

Very happy and hopeful that artificial intelligence can positively affect my country.

A hug.

By Lim K Z

Jan 9, 2019

Really love your interviews with the prominent figures in the AI sphere - very inspiring and insightful. Particularly like the advice given by Yoshua Bengio. Keep it up!!!!

By Matias M G

Aug 5, 2018

The excellent insight presented in this course gave me a way to analyze what am I missing instead of guiding me on intuition, allowing me to save a bunch of time and effort.

By Palash K

Feb 13, 2018

The things that are taught under this course are rare to find in one place. I feel this material is very helpful to build a strong base of deep learning. Thank you Andrew Ng.

By Zhiwei ( Y

Feb 2, 2018

Intuitions behind different concepts and techniques were exceptionally well-explained. The quizzes were well-designed whilst the assignment were extremely hands-on as always.

By NiuYaaa

Nov 8, 2017

By learning this course, I have known many tricks and intuition to make my neural networks work better. Thanks for the nice course, and I will keep learning the rest courses.

By Rajesh M

Oct 10, 2017

Overall the course is great. One suggestion however is to provide fewer instructions for programming assignments. The answers are almost obvious just reading the description.

By Gaurav M

Sep 2, 2017

Very Well structured course. Thank you Prof. Andrew Ng for sharing knowledge, and providing valuable tips on the subject matter. I am looking forward for the complete series.

By Mandavilli P

Dec 6, 2022

Better if edits of mistakes are made in the video itself instead of specifying pre hand Programming assignment should be made better for week 3 as it was very vaguely stated

By Dinesh D

Jul 15, 2022

Nicely designed - precise but covering all the concepts - course for non-domain people like me. Found this course very useful and was able to apply in my field of domain.

By PAWAN B

Oct 20, 2019

This course is amazing and I used to learn a lot of things from coursera. In this course, I learned the importance of hyperparameters and regularization in neural networks.

By Sudesh A

Jul 14, 2018

I like the drawing of the instructor in the saddle point video.TensorFlow introduction needs a bit more depth/explanation. There a major typos in codes.I enjoyed the course.

By J A M

Sep 25, 2017

Well done. Meaningful extension of the first class with nice segue into Tensorflow. Hope we can see a bit of Caffe and PaddlePaddle as well later on in the Specialization.

By Onuigwe V

Jun 17, 2020

This course give make you understand the concepts and intuitions of Hyperparameters. Very detailed. I recommend it to you, if you are a deep learning researcher or learner.

By Amey V

May 11, 2020

This course acts as a very good extension and wrapper to the first course and gives very crucial insights, without doing this course, only doing the first course is useless

By MD S A

Mar 25, 2020

Great insight into deeper concepts of deep learning. Lectures on different optimizers very helpful in understanding the basic concepts. Introduction of Tensorflow is great.

By Abhishek S

Jan 12, 2020

Verty good quality content, helps in understanding topics from basic which is not provided in every course, but needs more programming assignment to help us learn even more

By Catherine C

May 5, 2019

I really like to have finally a clear structure on how to tune the hyperparameters. I had to use a bit tensorflow before but it was a bit obscure, now it is finally clearer

By Prashant P

Sep 27, 2018

The programming exercises are great and the videos are just the right length. I appreciate Dr Ng deriving everything by hand on the slides, it helps with gaining intuition.

By Polina O

Dec 22, 2017

This course is a depository of tools that helps your NN be more perfect.

Batch normalization is pretty sophisticated topic. But programming assignment helps to get the gist.

By Bhaskar N

Oct 19, 2017

This is very well designed course to understand the hyper parameter tuning in a systematic manner other to convege the model faster. Thank you Andrew and Deeplearning team.

By David B

Oct 11, 2017

I would recommend these series of courses in Deep Learning to any PhD student who's domain lies somewhere else. It is a great tool to apply to your specific research topic.

By Tu L

Sep 20, 2017

Another amazing course of Professor Andrew. I have deeply understood many useful techniques to tune up DL models, which I used to adjust in a non-systematic way previously.

By Александр В З

May 16, 2021

Here was many new features for me, about DeelLearning NN training specific. Probably Tensorflow studing out of date. At least in such little volume. Better to learn Keras.