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

52,430 ratings
5,928 reviews

About the Course

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....

Top reviews


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.

Filter by:

5376 - 5400 of 5,860 Reviews for Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization


Jun 05, 2020

Some more details & programming exercises about batch normalization could have been provided.

By Sanket D

Jun 05, 2020

It could be updated to include more of the newer optimizations such as Bayesian optimization.

By Hakob J

Oct 11, 2017

It is very helpful course both for theoretical and practical aspects of Hyperparameter tuning

By Manpreet S B

Oct 03, 2018

good course, easy to understand and very nicely explained concepts about the neural networks

By Leonid M

Oct 05, 2017

It seems the major part of this course is taken from the original "Machine Learning" course.

By Chowdepalli R R

Jul 20, 2020

tensor flow is not understood properly else the course is very good and clean to understand

By 杨之龙

Apr 05, 2018

I have to complain why dont accompany videos with quiz and notes just like the ML coursera.

By Hyatt B

Jan 09, 2018

Content great! I'm not convinced Jupyter notebooks are the best approach for this material.

By Yen S L

Aug 31, 2018

Good explanations. But tutorials can be improved to demonstrate the various tuning effects

By Surya J

Apr 23, 2019

Great course to build intuition about tuning NN. Solid Foundation in very short duration.

By kritika

Mar 25, 2019

There was a lot of hand holding in programming assignments. It needs to be more rigorous.

By Vasilis S

Sep 26, 2018

Very informative course. The assignments are too trivial. Could've been more challenging.

By David D

Oct 07, 2017

Last programming assignments had some errors in them that could've easily been corrected.

By Bhargava P

May 21, 2020

Great content. Filled with rich techniques to improve models, hyperparameter tuning etc.

By Václav R

Feb 14, 2019

Could have focused a bit more on the tensorflow. Other than that - Great course, thanks!

By Rajiv C

Aug 25, 2017

It was fun to get to know other optimization techniques and how to speed up the network.

By Prajwal M H (

Apr 21, 2020

The difficulty of the course is medium. More time should be spent by learners for this

By Andrew W

Jul 30, 2019

Felt fast faced. But a good introduction to neural network hyperparameter optimization.


Nov 14, 2018

Course was really good, but I feel in tenserflow regularization should also be covered.

By Ahmed A

Oct 28, 2018

The course was very informative but the tensorflow notebook was buggy and needs fixing.

By Arjan G

Dec 07, 2017

Good course, but still has some minor issues in the assignments that needs to be fixed.

By Oleksandr T

Jul 29, 2019

Last code assignment is a mess. Looks like organizers have no intention to fix errors.

By Cindy Q

Apr 01, 2018

Week 3 feels a little rushed. The tensorflow material can be explained more in detail.

By Nicola P

Nov 11, 2017

Lessons are very clear and insightful. I would have expected more complex assignments.

By sree v

Sep 05, 2017

TensorFlow assignment is not good. There are many issues in submitting the assignment.