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
62,874 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

CM

Dec 23, 2017

Exceptional Course, the Hyper parameters explanations are excellent every tip and advice provided help me so much to build better models, I also really liked the introduction of Tensor Flow

Thanks.

NA

Jan 13, 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:

601 - 625 of 7,219 Reviews for Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization

By Pablo T

•

Feb 6, 2018

This class covers the gritty details on how to choose all the hyperparameters for a neural net. This is a vital step that isn't cover very well in other courses I've taken so far. Which makes this course uniquely valuable.

By Geethika I S

•

Jul 5, 2023

This course gave a in depth look at the hyperparameters and all the tools to tune and optimize neural networks. It was taught from the basic to the higher levels. Respect to the Professor and to the Deeplearning.AI team.

By Rahul K

•

Mar 31, 2020

Andrew NG in Machine and Deep Learning is like Bruce Lee in Martial Arts.

Starting from class 1, he covered each and every small topic and correlated those beautifully.

Feels lucky to attend this course.

Highly Recommended!

By Ramón R

•

Mar 30, 2018

Great course where we understand how to tune hyperparameters and how to improve our algorithms with regularization and optimization techniques. The basic concepts of TensorFlow and how to use it are also covered. AMAZING!

By Guillaume C

•

Dec 7, 2017

This is a great course. I would not imagine starting a Deep Learning project without knowing about Hyperparameter tuning, Regularization and Optimization. Andrew Ng is an amazing teacher. Learning materials are fantastic.

By Md S H C

•

Jul 16, 2020

Maybe a bit more Tensorflow basics could be covered. As a newbie, the Tensorflow assignment was a bit hard for me. Especially when I made some errors, it was difficult to find out what went wrong from the error messages.

By Taher K

•

Jul 5, 2020

It was a great course to dig into deep learning. In this course, I got a lot of intuition and insights from different methods of tuning and improving the neural network and how really like a specialist defines our model.

By Shishir K

•

Mar 9, 2020

A very handy course that introduces new topics like hyperparameter tuning, batch norm, softmax etc. Andrew NG gives a really good intuition for most of the concepts. Looking forward to other courses in the specialisation

By Jens L

•

Aug 6, 2018

Very good course to get a better understanding of how to optimize a NN by tuning the hyperparameters. It´s was also a very good introduction to tensorflow in the end and a very fun assignment in the end using tensorflow.

By Arvin S

•

Mar 10, 2018

It is a awsome course. Those familiar words, Hyperparameter, Regularization and Optimization, from the Machine Learning area, are all introduced by this course and the techniques will be used by the comming next courses.

By Mirantha J

•

Feb 11, 2018

I found the mathematical explanations to be very helpful for a deeper understanding of the key concepts in DL. Also the assignments give great explanations that helps to grab the ideas more. Thanks for this great course.

By Kumar S

•

Jul 3, 2019

Awsome course.Takes you deeper into how you optimize you neural nets.I have started loving to learn things once again.All credits to the instructor and everyone else who have put in effort to make the content this rich.

By Joshua G

•

Apr 10, 2019

Love the explanations and the fundamentals covered! My only feedback is you make it easier for students to download their finished content with all the data and utility scripts. Individually downloading files is a pain.

By Felipe C

•

May 29, 2018

Very nice course. The pace is good. For me the estimated hours per week was low, I ended up investing more time on the Course but I want a more thorough understanding of what's happening (I'm no expert by any means...).

By JEREMY S

•

Jun 5, 2020

This is a good course to improve our skills in hyperparameter optimization! I didn't know different optimization algorithm, the ADAM optimization is crazy and many other algorithms! good i'm ready for the third course!

By Erick A

•

Mar 14, 2019

I strongly recommend this course who anyone is interested on understanding what is going on behind deep learning algorithms. The lectures are very instructive and impel one to learn more and more about this discipline.

By Vengatramanan R

•

Jun 10, 2018

Thanks to Andrew and his team. The materials were easy to understand and the assignments helped gain confidence. My suggestion is to remove the 'fill in the blanks' type assignments and make it little more challenging.

By JONNAKUTI P K R

•

Jun 28, 2022

Thank you Prof. Andrew Ng for such a wonderful course and getting me interested in Deep Learning domain! The concepts were explained in a simple and most-intuitive way! Love the explanations of concepts in the course!

By Avinash

•

Aug 18, 2020

I feel that programming exercise of the last week of this course does not cover full of the third week videos.The concepts like batch normalization, hyper-parameter tuning. Other than that this course is very helpful.

By Dr. S V

•

Apr 27, 2020

This course is excellent, I understand all the hyper parameters and underlying concepts in tuning them to optimize Deep Neural networks. The introduction to tensor-flow and practical session on it is very much useful.

By Michalis P

•

Oct 11, 2019

Another great course, for getting your hands dirty with deep learning. Gained enough intuition about topics related with hyper-parameter tuning and learned about several optimization algorithms. Thanks for this course

By Nikhil V K

•

Oct 9, 2019

Enjoyed the course and programming assignments alot. Gained knowledge regarding Adam Optimization and batch normalization and learnt how to implement neural network in tensorflow. Teaching by Andrew Ng sir is awesome.

By Mallikarjun C

•

Feb 7, 2019

Excellent Practical advice on Improving Deep Neural Networks, Interesting talk with Heros of Deep Learning: Yoshua Bengio and Yuanging Lin and good programming exercises including nice introduction to using TensorFlow

By Danush V

•

Jul 30, 2018

Another masterclass from Dr. Andrew on Deep Learning. This course helps us in building a perspective on identifying significant hyper parameters influencing the performance of Neural Networks and how we can tune them.

By Zhuoqing F

•

Jul 22, 2018

I'm a biologist. This course explains basic component of deep neural networks, and it is the most clearly explained course I've even taken. Through this course, I could implement deep neural network even with numpy !