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
63,221 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

JS

Apr 4, 2021

Fantastic course and although it guides you through the course (and may feel less challenging to some) it provides all the building blocks for you to latter apply them to your own interesting project.

XG

Oct 30, 2017

Thank you Andrew!! I know start to use Tensorflow, however, this tool is not well for a research goal. Maybe, pytorch could be considered in the future!! And let us know how to use pytorch in Windows.

Filter by:

651 - 675 of 7,257 Reviews for Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization

By Mindaugas M

•

Feb 14, 2021

Good step by step guidance to gain initial intuition about optimization techniques and tuning! I like how it gradually builds layers of understanding of accumulated complexity by going through small pieces of it.

By Vignesh S J

•

May 4, 2020

Very practical breakdown of the various optimization techniques and how one can apply them. Also this was my first exposure to Tensorflow, I felt the assignment really made it easy to get started with tensor flow

By Sandil R

•

May 3, 2020

Very well explained with assignments where you can practice what you learn. The interviews with professionals were inspiring too. Learnt things that I initially thought would take me years to learn in a few days.

By Ananya R

•

Jan 27, 2019

Great Course, just like the rest in the specialisation! Really like the method of teaching!! Some sections of the assignment were coded before hand but would have been nice to be able to code them as well. Thanks

By Shubham S P

•

May 23, 2018

Full rating for this course, deals with the most difficult and challenging part of the deep-learning. Finding the right strategy for setting and optimizing the training. Thoroughly enjoyed, learning the concepts.

By Piyush K

•

Feb 12, 2018

Concepts are presented in very crisp and clear manner. Programming assignments have been heavily commented so that learners can focus on logic and functioning of the code rather than implementation and debugging.

By Zhixun H

•

Jan 27, 2018

The course materials scope, the instruction and homework are so excellent that you feel there is nearly no any obstacle for you to understand when you are leaning and practice when you just learn through homework

By Md R B W

•

Jan 18, 2018

Great continuation to the first course. Builds nicely on the necessity for hyper-parameter tuning and optimization. This course will take me a long way into reading, and understanding modern deep learning papers.

By Sumeet P S

•

Aug 24, 2017

Wonderful course. I am grateful for the detailed Tensorflow assignment at the end, since using such out-of-box libraries makes sense. But also the concepts underneath has been made very, very clear in the course.

By Wei-Chuang C

•

Aug 17, 2017

It's the easiest course for various deep learning techniques I have seen so far while touch base on critical concepts. Programming assignments are not hard to follow even for someone with no technical background.

By Alessio G

•

Aug 15, 2017

The topics covered in this course make the difference once we train our model. Thank you Andrew for this amazing course and your outstanding explanations!! I love the Hero interviews and the jupyter assignments!!

By Marcelo F Z

•

Jul 4, 2022

Great course! Andrew NG has a talent for explaining the details of applying Hyperparameter Tuning, Regularization, and Optimization. Thank you, Coursera and DeepLearning.AI for providing such fantastic material!

By idrees k

•

Jun 19, 2021

As usual, Andrew is best at teaching anything related to deep learning. The course is well organised and very informative. It also introduces you to TensorFlow which is an important framework in machine learning

By G R S

•

May 12, 2020

An excellent course indeed. I will be proceeding to the next one in the specialization. As usual, a lot of math, but explained thoroughly and excellently with aplomb. The TensorFlow framework sure is convenient.

By Selim S

•

Mar 18, 2020

Excellent course, the complex notions are made easy. The programming assignments allows to apply the content of the lessons in an easy and very instructional way. Looking forward to complete the specialization.

By Pedro J

•

Aug 17, 2019

Highly recommend the course. Andrew go deep on the detail and nuances of deep learning giving the math and the practical application laying a good foundation on the understanding and application of deep learning

By Chien D

•

Aug 10, 2019

- Very good explanation. I have learned a lot about hyperparameter tunning, batch norm. Beside that, this course also introduces about tensorflow framework, which make easier for me to create and fine-tune model

By Keith R

•

Apr 6, 2019

Great course that starts to delve deeper into neural networks. Also, there is a good introduction to using Tensorflow for neural networks that was quite useful.

Great presentations and good programming exercises.

By Abdullah K

•

Nov 7, 2017

I just love this series of courses. The best courses I have ever taken online, and I have taken online learning on most major platforms. Huge shout out to Andrew Ng for producing such excellent set of materials.

By PIUS G

•

Feb 20, 2021

Excellent course. Andrew makes the concepts easy to follow and the programming assignments also help to get a more practical understanding. I am glad I now understand the big words that scared me some time ago.

By Dipo D

•

Dec 22, 2019

This course really helped me to make my concepts crystal and clear. Previously, I read books and slides on this topic; now by doing this course it helped me grasp the topic well. Thanks a lot, Andrew Ng and Co.

By Srivathsan A

•

Aug 2, 2018

This course is for you if you have the data and was looking for experimenting with the data using the neural networks. This course takes the nn to the next level, where several hyper-parameters were introduced.

By Yaron K

•

Apr 7, 2018

Clearly critical if you're programming a Neural network. But also critical when using a software framework to build NN - since these have many parameters. This course explain what they are and how to tune them.

By Gokul K

•

Dec 26, 2017

This is an amazing course! It will take more than 3 weeks if we are not familiar with the concepts already. But we really get to learn all the industry standard techniques in great detail. Throughly enjoyed it!

By Sebastián R

•

Sep 30, 2017

Again, some of the best material I've found online. I've never seen several things explained as clear as in this course. Including Momentum, RMSProp, Adam, hyperparameter search, hyperparameter distributions...