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
63,175 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

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

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:

1301 - 1325 of 7,253 Reviews for Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization

By Elvis S

Jan 18, 2019

Loved this part of the code... it allowed me to understand more about the optimization and regularization tricks such as RMSprop and Dropout.

By Ranfi J C d A

Oct 29, 2017

Este curso es muy importante si lo que quieres es, no solo aprender a crear Redes Neuronales, si no hacerlo de una manera eficiente y rápida.

By amir h r

Nov 16, 2022

it was such a fantastic course for me.

the programming assistance was amazing and of course difficult.

thanks mr. ng for providing this course

By 权泽平

Sep 27, 2022

A very good course. A small drawback: The three parts are somewhat seperate, so it's a good idea to give an overall review quiz in the end.

By Manuela R

Jun 17, 2021

I think the course is very well planned, it is clear, easy to follow, the exercises help to understand the concepts. I totally recommend it.

By Ajit B

Jul 9, 2020

Very nice course! I wish there was also a tensorflow course as a companion. Thank you for demystifying neural networks and their frameworks.

By Suhail M

Jun 23, 2020

I just do not have words to express what i am feeling now ,, definitely confident and more confident to m move ahead in this specialization

By Aniruthya

Dec 1, 2019

Good material and course content and very neatly organised. I hoped more would be covered on topics pertaining to different regularisations.

By Deleted A

Jul 9, 2019

Top course which teaches all the basics and contemporary neural networks approaches! Well structured, good content, and some solid practice.

By Hichem B

Mar 22, 2019

Very good course, with most importantly intuitions given and also some (superficial) theory underlying the principles of NN and other stuff.

By Parth A

Jul 20, 2018

Amazing course! Thanks for explaining the practical aspects of modeling. Looking forward to learning project structuring in the next course.

By jyoti p m

Jun 5, 2018

It was one of the most complex, yet so lucidly explained topics in deep learning. Kudos to Andrew Ng for pulling this of with such elegance.

By Jialie ( Y

Jan 18, 2018

Very good course, the lectures is about the basic Technics tghat will speed up and optimize the DNN, also have an introduction of Tensorflow

By Anand G

Nov 21, 2017

After the introduction to the DL and AI world, it was great to understand the things that make it robust and to apply it in a real scenario.

By Răzvan I

May 1, 2022

I feel really satisfied about the number of optimizations I learned as well as the mathematical intuition behind every optimization method

By Kalpak S

Oct 14, 2020

An Excellent course to dive into the hyperparameters of the Neural Networks. Provides great hands-on expertise and builds on the intuition.

By MR. S R S

Sep 4, 2020

Insightful peek into the world of hyper parameters tuning and batch normalization and a good introduction to Tensorflow.

highly recommended!

By Md. W T R ,

Aug 20, 2020

Again a big thanks to Mr. Andrew Ng and his team for helping me achieving the knowledge.. Hope I will get a big return out of this course..

By 김홍숙

Jul 26, 2020

It's full of practical knowledges that can be useful but never touched in other courses.

It is MUST TO KNOW, if you're practioner on DL, ML.

By Rodolfo V

Jun 15, 2020

The course need more exercicies with framwork, this is the only thing I could thought to help to make better that amazing course. Thank you

By Ivan G K

May 21, 2020

Learned quite a bit in this course about proper tuning techniques of Neural Networks as well as a pretty decent introduction to Tensorflow.

By Nihila B

May 19, 2020

The lectures were very clear that I now feel like I'm finally getting somewhere towards my career. Thank you for this amazing opportunity.

By Huong H

May 29, 2018

Excellent course! It instructions, the quizzes and the programming exercises are wonderful. They make me to understand the concepts easily.

By Ishwarya M

May 5, 2018

Course if full of rare intuitions you could get only from someone like Andrew Ng. Thank you Andrew & Team for putting this course together.

By pradeep m

Jan 10, 2018

It would be great if the lecture notes in pdf format can be provided at the end of module, as similar to Machine learning course by Andrew.