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
63,068 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

YL

Invalid date

very useful course, especially the last tensorflow assignment. the only reason i gave 4 stars is due to the lack of practice on batchnorm, which i believe is one of the most usefule techniques lately.

NC

Invalid date

Yet another excellent course by Professor Ng! Really helped me gain a detailed understanding of optimization techniques such as RMSprop and Adam, as well as the inner workings of batch normalization.

Filter by:

1351 - 1375 of 7,239 Reviews for Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization

By BIN N

•

Jun 16, 2019

I am happy to learn a lot about Hyperparameter tuning. I think that I will refer to this course when implementing neural networks myself.

By Arun K

•

Mar 9, 2019

Really an awesome course. Learnt about the math behind major Deep learning algorithms. A fun course and loved the saddle point reference.

By alrojas68

•

Nov 15, 2018

This course covers so deep insight on what is like to train Neuro Networks. Extremely useful. Thanks a lot to Andrew Ng and all the team.

By Poorna J

•

Aug 29, 2018

The Course that gave me confidence to overcome the performance constraints of ANN - now I have a bag of tricks to improve the performance

By Huifang L

•

May 4, 2018

The professor did a great job in explaining the intuition and shared a lot of practical tips. Programming homework is very well designed.

By Jun K

•

Apr 21, 2018

A wonder course, which is always the case for Andrew's course. It was nice to learn what's happening with momentum and Adam optimization.

By Aashish K

•

Jan 8, 2022

I use to be always scared by the terms like Hyperparameter Tuning, Regularization. After this course, I am pretty comfortable with them.

By duc-thanh t

•

Mar 10, 2021

The course is a perfect balance between theory and "hands on" assignment to familiarise yourself with the optimisation of neural network

By Aditi S

•

Feb 8, 2021

This course provides great insights into multiple ways of improving a deep neural network in practice. Well structured and rich content.

By Andrzej C

•

Feb 1, 2021

One of the best courses I've attended; gives a lot of intuition, but some more programming exercises, even optional ones would be great.

By Ralapalli S N M B

•

Dec 21, 2020

Just reading a book of all these concepts is not enough to have a deep understanding. This course is just right to learn what is needed.

By Rafat R

•

Sep 13, 2020

Some of the lessons were quite confusing and still not clear but Mr Andrew was absolutely brilliant. Loved the time spent on the course.

By Shamith A

•

Jun 24, 2020

The theory and explanation is awesome. But, I wish the last programming exercise will be adapted to TensorFlow 2 (instead of TensorFlow)

By Keshav B

•

Jun 1, 2020

It was definitely a bit more difficult than the previous one, but also it was just as much fun doing this course as the previous one. <3

By Great S L

•

Jul 4, 2019

This class is amazing for those who want to start their career in the world of Data Science with Neural Network!!! Highly recommended!!!

By Rahuldeb D

•

Jul 23, 2018

Another awesome course. Things have been discussed in great details. I would like to thanks Coursera for offer such a wonderful course.

By Sayar B

•

Jul 5, 2018

Professor Ng explains complex concepts with such ease. Uses great examples to illustrate the 'why' aspects of everything in this course.

By Rishab R

•

May 9, 2018

Another excellent course which builds on the material from the previous course.

Thanks Andrew for presenting it in the best way possible.

By Xiaolong L

•

Feb 27, 2018

Very helpful course. There are a lot of practical tips covered. Also, the explanations to why the techniques could work is very helpful.

By Sami

•

Feb 15, 2018

very useful course to understand how to tune your algorithm for better results and accuracy, also how to manipulate your hyperparameters

By Boon H T

•

Feb 5, 2018

Lots to learn about parameters that effect the neural network and various regularization and optimization techniques for neural network.

By Ankur G

•

Dec 26, 2017

This course provides a lot of information that ML researchers obtain through practice. This course will help beginners get a head start.

By Gek H C

•

Dec 14, 2017

I love this course. Videos are very well split into short sessions, clear explanation, very good examples, quizzes and graded tutorials.

By Jitendra M

•

Oct 9, 2017

Andrew Ng has no parallel in bringing absolutely complex concepts down to a level that idiots like me can understand and apply. Salute!

By Kishore V

•

Sep 2, 2017

Programming assigments guide you through everything you need to know about choosing parameters and implementing optimization algorithms.