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:

751 - 775 of 7,257 Reviews for Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization

By Parul P

•

Apr 9, 2023

I had to go over some videos multiple times as this a very deep topic.. What would be great is having more programming assignments in the style of Kaggle competitions. You can keep them optional.

By Sepehr S

•

Jun 15, 2020

The material was interesting. TensorFlow was very brief. What you basically do in the homework is to copy paste the code. But I do not think that I would be able to write the code from the scratch

By Lakshmi T

•

Sep 23, 2018

Thank you! Great lecture videos and programming assignments with a lot of help built in. I was able to figure them out. Need more practice to master the materials. Thank you! This is a great start

By Ashutosh S

•

Jul 28, 2018

This is a very important part of the deep learning course, Generally people skip such type of things but here it is deeply explained and a hand on practice assignment makes it totally transparent.

By Bruce C

•

Dec 8, 2017

In this course, I learned a lot of important concepts and useful implementation techniques. Even though I do have some implementation experience before taking this course, it's still very helpful.

By Gurumurthi V R

•

Oct 1, 2017

Excellent pedagogy and a simple but effective breakdown of the DL principles in a way a beginner can understand and later appreciate after delving deeper into the subject. Very highly recommended.

By Alvaro P

•

Jan 26, 2021

Andre does a great job explaining concepts and intuitions, and the contents of the course are up to date and relevant for anyone looking at getting started with neural networks and deep learning.

By Annwesha P

•

Jun 11, 2020

It was a very interesting course hence didn't even take much time to get completed. It gives a comprehensive overview of deep learning frameworks and the skills needed to optimize your algorithm.

By Bhanu P M

•

Jun 4, 2020

The course material is great. Assignment problems are very engaging and allow us to practice all the concepts that we learn within and before that week. Andrew NG is great at teaching concepts .

By Samiul I

•

May 31, 2020

Highly recommended after completing of Neural Networks and Deep Learning.

Good explanation about regularization and other optimization technique.

The last assignment of tensorflow is very useful.

By BuÄŸra C

•

Apr 12, 2020

Exceptional as always. Online courses as engaging as the ones Andrew Ng teaches are a delightful rarity. This course was a joy to participate in and I feel throughly satisfied with my experience.

By LI X

•

Aug 24, 2018

I think we as students should have more coding exercise, the coding assignments are too simple if considered as a school-teaching course. We gotta to find some extra Deep Learning projects to do.

By Sean C

•

Feb 15, 2018

A valuable course in enhancing one's ability to properly identify the correct Hyperparameter to tune according to the situation - a critical task in day-to-day debugging & tuning of an algorithm.

By Livakivi

•

Nov 13, 2017

Another great course in the deeplearning.ai specialization, all the given topics are clear and understandable, with the amazing addition of finally getting to deep learning frameworks in the end.

By Bruce M

•

Aug 6, 2020

great course; love the AI heroes sessions - nice quick insights into current research; and enjoy some of the historical aspects as well ... takes me back to my early AI/image understanding days.

By Yong B S

•

Jun 15, 2020

the course is great! I've learned more hyperparameters. The course has teaches me how to add regularization and optimizations. That is another important part of Deep NN. Thanks to the professor!

By Akhil G

•

Jun 15, 2020

A Very Well Structured Course. I learned a lot and enjoyed the way in which everything is explained. Each topic is discussed in great detail with both pros and cons of each Deep learning method.

By L V K S R B

•

May 10, 2020

Great course!!!! Helped me with getting better intuitions on how to develop a simple neural network with normalising inputs, regularisation, optimising algorithms, hyperparameter tuning, etc ...

By S. M F

•

Mar 19, 2020

The specialization is getting more and more interesting! This course was really important to learn improving a model. Now I understand what's going under the hood of basic TensorFlow operations!

By Omar S M

•

Aug 30, 2019

This is an excellent course in which Professor Andrew Ng explains all the concepts and methods related to various optimization techniques and ways to improve neural networks, in a superb manner.

By AKANSH M I L S

•

Aug 13, 2019

I found that the concept of Deep learning hyper parameter tuning were nicely taught and assignments were also designed very well. However, I am not able to learn much about tensorflow framework.

By Ryan W

•

Jul 31, 2019

Great course. Wish it had slightly more in terms of turning hyper parameters with the Adam optimization. Liked the tensorflow framework at the end; I hope it is expanded upon more in the future.

By Kai C

•

Nov 3, 2017

Through this course, I learnt how to tune hyperparameters and a set of optimization for the train process of neural networks. Further I got the opportunity to play TensorFlow. I really enjoy it.

By Sudipta C

•

Sep 14, 2017

Well structured course and very good material. Thoroughly enjoyed Prof. Andrew Ng's lectures and leart a lot from them. I only wish the programming assignments were a bit tougher than they are.

By Alexander G

•

Sep 3, 2017

Thank you for your explanation that are very useful and clear! You present so much difficult material but you do it very concentrate. Thank you for practice and excercises that are very helpful!