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:

676 - 700 of 7,257 Reviews for Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization

By Huy N

•

Jul 8, 2020

This courses enables me to speed up my Gradient Descent algorithm by several ways. Additionally, I have opportunity to approach programming framework Tensorflow, which is really concile for me in DeepLearning.

By Prasath K

•

May 24, 2020

This course really helped me to get into mathematical intuition used in deep learning and motivates to learn computer application by understanding mathematics behind that instead of programming using framework

By AKSHAY K C

•

Jan 28, 2020

Great follow-up course by the instructor after the Neural Networks Course. Got an in-depth understanding of hyperparameter, regularization, and optimization. Kudos to the team for designing such a good course.

By Ara B

•

Oct 20, 2019

It i very good course! I would suggest to have multiple smaller programming assignments during the lectures specially when the material is explaining the math on regularization, optimization and normalization.

By Murad O

•

Nov 8, 2017

I found this course, as someone with a bit of experience in math and machine learning, more useful for me than the first course. But in all the cases I find the specialization super useful, and very well done.

By Sanchit

•

Oct 18, 2017

Again really simplified way of teaching complex stuff.

Some additions for future coursework:

1.) There is some project at the end of course

2.) Also, if you could share arxiv links to relevant research going on

By Alvaro

•

Dec 26, 2021

It is simply awesome the quality of the deeplearning.ai organisation courses. I am very glad to have found this specialization course, it has the perfect equilibrium of theory and practical lessons.

Thank you!

By Vishaal K M

•

May 4, 2020

Who am I to review Andrew Ng's course? He's a good mentor who knows what he's doing and it was fun doing the course with him. No problem with the course whatsoever which cannot be solved with another rewatch.

By Jihwan M

•

Sep 15, 2017

You get to tune your already built neural network from the previous course. You will definitely be amazed by how the presented tuning strategies can speed-up your network or even produce a better performance.

By Harshit G

•

Jul 12, 2020

AMAZING COURSE! Really helped learn a lot about how to understand and think forward about what to do next after seeing the different accuracies! Hope to implement these learnings in my projects soon enough!!

By Alexandru L

•

Apr 26, 2020

This course will help you understand what is behind an optimizer, and what a machine learning framework is doing under the hood. Also you will learn the first steps into TensorFlow framework. I recommend it!

By Rahul M

•

Apr 6, 2020

It was a great learning multilayer neural network and all the necessary detailed information to build one. The course suggests most of the successful ideas to tune the networks to achieve better performance.

By Sonal P R

•

Sep 2, 2019

The course was awesome. I'm very much thankful to Andrew Ng for providing his valuable knowledge and insights on deep learning. Best educator ever! Looking forward to more course on deep learning and Python.

By Shreyas R

•

Aug 19, 2018

I thoroughly enjoyed the course. It was short and sweet but totally loaded with a lot of new things. The introduction of tesnorflow and the opportunity to use it to make a neural network was a key take away.

By debraj t

•

May 6, 2018

Very helpful and enlightening. I liked the fact that intricacies of hyper-parameter tuning and BN were covered before introducing Tensorflow.

I felt a few more exercises in Tensorflow would have been useful

By Prashant K J

•

Oct 29, 2017

Builds on the first course brilliantly. As anyone working in analytics will double it, tuning parameters does the actual trick. The course gives clear explanation of what works & why that works while tuning.

By akshay b

•

Sep 28, 2017

It is the best course in introduction to tensorflow and batch normalization hands down.Although the minimal mathematical approach is followed still the course hits the conceptual homerun.

Absolutely brilliant

By Gabriel V

•

Dec 30, 2020

Es realmente bueno como se ha realizado la introducción a los frameworks después de haber tenido intuiciones de la construcción de las Redes Neuronales desde cero, estoy realmente satisfecho con este curso.

By sankalp s

•

Oct 10, 2020

Well detailed course for students its just right as it is good for beginners as well as experts, and for ones who want to follow good practices building Deep NN.

Give your full try on quizes and assignments.

By Kashyap B

•

Jun 24, 2020

Excellent course by Andrew again. That mathematical interpretations were really presented well.But I would suggest to put an additional optional assignment and video for Tensorflow 2.0 along with keras api.

By CHENGQI L

•

Nov 14, 2019

The classes are easy to understand, practical assignments make me apply the theory which I learned from the class. Combination of practical issue and theory trained me a deep understanding of Deep Learning.

By Foad K

•

Oct 7, 2019

This is a great course. Andrew explains the concepts so organized with well-thought examples. The course is clear, teaches the fundamentals and allows the student to think independently for future projects.

By Guokai Z

•

Oct 28, 2018

Thanks Andrew Ng for this excellent course. I learnt a lot from this course about parameter tuning and regularization. These technics are very practical and helpful to machine learning project construction.

By Dietrich B

•

Oct 15, 2018

A great introduction into Deep Learning with TensorFlow!

The cours would be even better, however, if the typos and faults reported in the discussion forum would be corrected in the course material as well :)

By Lukas R

•

Oct 14, 2018

Thank you very much for making this class possible. I have learned a lot and if needed I went to forums where many people where willing to help and I founded my solution to a problem in no time! Great work!