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:

801 - 825 of 7,253 Reviews for Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization

By Ramon S

•

Apr 5, 2021

A really good continuation of the lessons learned in the first course, and a gentle introduction to TensorFlow. Overall a 9/10, it would be a 10/10 if the assignments were more challenging.

By Karandeep

•

Feb 3, 2020

Course is very good but better notes should be provided as it is a paid course. Also, it would be better if assignments are little challenging and hints shouldn't be provided at every step.

By Yingzhao L

•

Nov 21, 2019

Again this is another great course continuing the first course. The only thing to say is that TenorFlow assignment needs to be update to version 2 in order to benefit the simplified syntax.

By Aristotle M

•

Sep 11, 2019

This course was very helpful in that it delved into more of the practical aspects of building deep neural networks. It builds on the first course very well, and I would highly recommend it.

By Sumanaruban R

•

Oct 24, 2018

This course helps to become pro/expert in DL/ML within a short period of time. Andrew shares his decade long experiences and best practices in this course. I strongly recommend this course.

By Heyang W

•

Aug 16, 2017

Great hands on experience of tuning and tensorflow tutorial. Unlike the old ML course and the one taught by Hinton, this course prepare you for the newest framework instead of Octave staff.

By Emmett B

•

Aug 26, 2022

Good course which clearly explains all the material, though ocassionaly there's a really high pitched noise in the background of the videos which would be nice if it could be editted out.

By Goutam K J

•

Jul 22, 2020

I have understood the basic math of neural networks, also how we can tune the parameters to optimize the neural network, so that it perform better.

A Very Very big thanks to deeplearning.ai

By José R H S

•

Jun 13, 2020

Me pareció excelente y al punto. Todos los consejos dados son realmente aplicables y se entiende la razón de cada uno. Los ejercicios no son excesivamente complejos y están bien redactados

By Mustafa K

•

May 22, 2020

Amazing course. A must course for everyone who wants to save a bunch of time by making their training model efficient. Andrew Ng is an amazing instructor and makes every lesson look easy.

By HISASHI O

•

Feb 23, 2020

January in this year, I did not know this course. At that time I want understand TensorFlow but I didn't know where should I begin. After finish this course, I suggest anyone, this is it!

By Robin R

•

Oct 18, 2019

Words cannot explain how important this course has been for me. Andrew NG proves. Everything that has intuitiion, is really easy to learn. Very few person in machine learning who kills it.

By liuchunhui

•

Nov 9, 2017

perfect course for deep learning fresher, this course mainly introduce fundamental knowlege to us, and cover wide aspects,such as optimization algorithm, hyper parameters tuning and so on.

By Amirhossein T

•

Oct 14, 2021

The superiority of this course over the rest of the content is expressed in very simple language and the design of notebooks is very useful, which makes us follow the content much better.

By Kat R

•

May 10, 2021

The clear, concise step-by-step explanations were great, and the exercises easy to follow. Perhaps too easy though, I wish the assignments would prompt me to write more code from scratch.

By Abir E

•

Feb 25, 2021

I love the course, you learn everything about hyperparameters search and tuning, optimization algorithms and many many other details (profound content that you can't find anywhere else! )

By Ernest W

•

Aug 15, 2020

Ammaaaaziing course...!!! simply amazing. I believe Andrew is the best instructor. I now understand the underlying computations that are used by deep learning frameworks like Tensorflow.

By Devang P

•

Jun 17, 2020

This course is giving the Path/Strategy that how to deal with Deep Neural Networks and make Neural Networks work more accurately by tuning the Hyperparameters and Optimization Algorithms.

By s p

•

Jan 15, 2019

I got a very good understanding about how to what are the parameters I can tune, regularization methods, and different gradient descent alternatives which can be used through this course.

By Alam N

•

Aug 30, 2018

Thanks to Coursera team for organize this course with one of the best platform for new learner from top class instructor and researcher of top rink universities. Also thanks for free aid.

By Vrajesh I

•

Jun 4, 2018

Teaches some of the most important concepts in deep learning in my opinion, and you also learn to use tensor-flow which is one of the most versatile python libraries in todays coding era.

By Namhoang

•

Jun 30, 2023

The course is great, Andrew Ng. has a very impressive way to explain the abstract concept that may require a serious understanding of related matters. Thank you for making a good course.

By Fabio K

•

Aug 26, 2020

Very good. Very nice and easy to understand the brief explanation and hands on with Tensorflow. Now it all makes sense. The mathematical background given in course 1 is indeed essential.

By Tobie

•

Oct 20, 2017

Really well structured course that builds on the techniques learned in the previous class and teaches lots of new information quickly and effectively. I feel like I'm learning so much!!

By Brian D

•

Jul 21, 2021

Good content to help understand how different techniques can increase, or decrease, the success of your models. Really shows how little tweaks in certain hyper params can go a long way.