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:

1326 - 1350 of 7,253 Reviews for Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization

By Tsang S H

Nov 26, 2017

Hyperparameter tuning usually mentioned in papers without any systemic workflow. But detailed tuning steps are mentioned in this course !!!

By Agam B

Oct 23, 2017

Fun and engaging, and very accessible too! A great overview of various optimization algorithms, and a great introduction to Tensorflow too.

By Pablo V I

Oct 21, 2017

Awesome curse If you want to understand the mathematics behind some deep learning techniques. Highly recommendable curse! Thanks Andrew Ng!

By Rafael A H P

Oct 20, 2017

Very useful. Goes through a lot of recent advances to optimize deep learning performance. The exercises does feel easy and straightforward.

By Pedro H M P

Apr 28, 2020

Curso bem ministrado, com um olhar profundo para o tema. Gostei muito, supriu a necessidade que eu tinha em entender a fundo redes neurais

By Revanth P

Apr 9, 2020

It is a good breakdown and logical progression of the need and evolution of parameters and hyper-parameters. Throughly enjoyed the course.

By Х. А Р

Apr 3, 2020

In spite of my strong mathematical background I found many interesting features for using maths in Deep Neural Networks. Excellent course!

By SHUBHAM E

Mar 15, 2020

Okay with week 1 and week 3 but you need to improve the motive behind presenting week 2. Also what was the purpose of batch normalization?

By Vinicius d A R

May 3, 2019

Excelente curso para um entendimento mais profundo sobre os parâmetros que compõem uma Rede Neural. Parabéns ao mestre e mentor Andrew Ng!

By Arsalan J

Jan 6, 2019

I believe a approach Sir takes while teaching the course makes it comparatively easy to learn the very difficult concept of deep learning.

By Kunihiro O

Dec 22, 2018

very great useful. I want to learn compute science (bachelor's degree)by top 10 of university.

that Mooc is success. I want more learning

By Mukund A

Nov 29, 2018

Awesome! Very helpful & interesting. Looking to take up more courses in future.

Best way explanation. Awesome quiz & programming exercises.

By Deepak S

May 25, 2018

I was excited to learn TensorFlow and this course provides the foundation for that as well as continue the concepts from Course 1

Thank you

By Junde L

Nov 25, 2017

Thank you so much Andrew. This course sharpens my understanding about deep learning, and lets me know the powerful function of Tensorflow.

By Ao X

Nov 1, 2017

Still a good intro course for DP. But most of the techniques are not really based on math but tricks. Maybe it's part of the nature of DP.

By Gustavo S

Nov 1, 2017

Covers optimization algorithms, Minibatch Gradient Descent, with Momentum, Adam, Xavier initialization, etc. Well-structured and objective

By Wessam A

Oct 3, 2017

Real build-up on the great intro course. Gives valuable practical insights on how to use the techniques learned in real life applications.

By R S k

Aug 28, 2023

We learn about all the parameters we use to tune a neural network including learning to use the tensorflow framework. Very uesful indeed.

By IGNACIO H

Jul 25, 2022

Muy buen curso para entender y aplicar herramientas que hacen más eficiente el uso de DNN. Excelente balance entre profundidad y práctica

By Mahdi K B

Jun 5, 2022

Great Instructor, Superb and up-to-date material, accessible for not math savvies,

Best possible instruction ever for such a heavy topic.

By SHAHID K

Jun 2, 2022

Best course in deep learning , this course is a gem , usually the methods and technics taught in this course aren't taught in academics.

By Taha A A

Nov 2, 2021

The course content were well organized and so good but the programming exercises were a bit easy and were implemented by a large portion.

By Anirban S

Apr 25, 2021

The lucid explanation provided by Andrew Ng goes a long way in helping the students build core concepts in a logically structured manner.

By Hαsίβυπ R

Aug 31, 2020

All are the Courses are just amazing and helpful and Dr. Andrew Ng is great instructor .... i just loved his way of teaching.... Thanks !

By Bilal Z

Jun 30, 2020

It was a fabulous experience taking this course.I learned a lot,although not 100% as majority of concepts were new but to certain extent.