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
62,870 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

AS

Apr 18, 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

AM

Oct 8, 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

Filter by:

701 - 725 of 7,219 Reviews for Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization

By Weiran H

•

Feb 3, 2020

Good starter-level course, but in my opinion, the third assignment is not so well-designed. It does not even contain the content of the third-week course, for example, BatchNorm and hyperparameter tuning.

By Ali A

•

Jun 2, 2018

I don't have much to say about this course except for hats off to team coursera on the yet another amazing material and delivery. I highly recommend it for any enthusiast beginning their DL study journey.

By Jitendra N P

•

Mar 25, 2018

This is an excellent course on practical aspects of Neural Nets and Machine Learning. As always Prof Andrew Ng is brilliant in elucidating complex concepts and techniques in simple and intuitive language.

By Luat N

•

Sep 23, 2017

Of course, it's a wonderful teaching approach that I would recommend to everyone. The course provides a much deeper understanding of Deep Neural Networks for how to build model that works at its optimum.

By Amit P

•

Aug 19, 2017

Andrew has an exceptional gift of simplifying the math. I finally understood momentum and Adam. Also, my understanding of batch norm improved. Happy with my progress based on the materials in this course.

By Frantisek H

•

Sep 4, 2020

Excellent course - Andrew's teaching is what's so needed in the machine learning community. He explains concepts properly so that one truly understands them, and thus knows what to do when applying them.

By Pedro d T M

•

Jul 6, 2020

It is an axcellent intro on how to tune hyperparameters of a neural network. The level of details seems to have decreased from the previous course of the specialization, but still is an excellent course.

By Diego J R C

•

Jun 7, 2020

This course had valuable information about hyperparameter tuning, regularization and optimization. Now I have a better understanding of more advanced criteria to improve my neural network implementation.

By Leeladhar D

•

May 12, 2020

very practical thing is learned from this course. Often we developed machine learning algorithm but if algorithm has need some polishing to improve the performance where this course will really helpfull.

By Yun-Chen L

•

May 11, 2020

I figured out what could I do when the model is overfitting. I learn lots of optimization methods, liked mini-batch gradient descent. RMSprop. momentum. Adam, and I started to learn TensorFlow Framework.

By 18IT042 C J

•

May 3, 2020

In this course, I learned some of the best practices used to increase accuracy and decrease training time of model. I was also introduced to Tensorflow, and now I can create different projects by myself.

By CK46

•

Jan 16, 2020

This course simplifies how to improve neural networks. It provides systematic approaches to hyperparameter tuning which is very important and helps the time and effort required in developing good models.

By melanie b

•

Mar 15, 2018

Excellent instruction on the most highly utilized optimization algorithms and how to implement them. Also provides great intuition on hyperparameter tuning essential for tackling complex neural networks.

By ujwal v

•

Mar 3, 2018

However important the Neural Network model is, its exactly equal importance to create Parameters that make the NN perfect and usable, this teaches the In and Out of the Parameters selection for NN models

By Bahadir O

•

Sep 30, 2017

Prof. Ng makes you understand all the hard subjects with ease. I'm starting to believe he's actually a neural network specifically trained for teaching people - Never seen a human teach this good before.

By Aaryaman B

•

Sep 3, 2020

You know what, this guy and his team know the best way how to keep you indulge and make you understand every bit of code you write.

Great course, just needs some upgradations when it comes to TensorFlow.

By XIAOYANG S

•

May 17, 2020

This course is excellent that helps us know how to implement one deep learning model, how to optimize it, and how to avoid a few issues in coding. I also learned a lot about Tesnsorflow from it. Thanks!

By Richard G

•

Apr 23, 2019

Really good basic theory explanation, I took Udacity Deep learning NanoDegree too, this one actually gives more detail explanation, Udacity is more like a higher level and more advanced project practice

By Yosuke N

•

Feb 15, 2019

Great course to learn basis of the DNN, Tensorflow, and especially direction of hyperparameter tuning will be very useful knowledge on my job. It will help us escape from maze of parameter optimization.

By Meghal S

•

Aug 30, 2020

This course helps to learn TensorFlow for Deep Learning application. Deep Learning neural networks which are implemented in Neural Networks and Deep Learning Course is implemented here with TensorFlow.

By Karan

•

Jul 20, 2020

Wow, this course was very thorough and deep into the underpinnings of deep learning. Thank you Coursera, deeplearning.ai, and thank you Andrew Ng.

You make learning so much fun and accessible worldwide.

By Francesco C

•

Aug 15, 2019

I appreciated the explanation of the different techniques (esp. the optimization ones) covered by the course, as well as the effort put in making the notation as simple as possible. Definitely helpful.

By dan s

•

Oct 27, 2018

This was a fantastic course. Andrew Ng explains these concepts so clearly and provides practical examples that enhance the learning. Thanks again. I just loved the course as well as its predecessor.

By Ravibhushan K

•

Nov 27, 2017

This is awesome course. I never seen any tutorial like this on internet. Your language is simple enough and concept are crystal clear. once again Thanks for giving me opportunity through Financial Aid.

By Alex M

•

Oct 25, 2017

Continues a great specialization track. The coding is made to be not at all difficult but still manages to impart the intuitions, such that the lectures and coding assignments do complement each other.