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:

6501 - 6525 of 7,238 Reviews for Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization

By Jonathan G

•

Aug 9, 2020

Es necesario que actualicen los notebook por ejemplo el de TensoFlow ya que esos códigos no corren bien con la nueva versión

By Alonso O O

•

Apr 7, 2020

This course was a little bored for me. I already knew a little bit about hypertuning so I felt that the course moved slowly.

By Omar S

•

Oct 29, 2017

Provides a good code skeleton to build a neural network, but would unlikely have one poised to do improvements on their own.

By Nikolaos P

•

Nov 29, 2021

Very good course, but I would expect some hands on hyperparameter tuning (using maybe an additional programming assignment)

By Kevin C

•

Oct 28, 2020

Está bueno el curso pero quizás lo más interesante sea el uso de TensorFlow al final para que todo empiece a tener sentido.

By Om S P

•

Jul 19, 2019

Some assignments, even though I get the same result as the output given, it get marked as wrong... Please try to rectify it

By Victor P

•

Oct 26, 2017

Very good course from the excellent Andrew Ng.

Some typos and some glitches in the video, hopefully it will improve in time.

By Alex N

•

Sep 12, 2017

Good pace

Only drawback is that some of the safe checks are wrong in the programming assignments, even with the right seeds.

By Khalid A

•

Sep 14, 2019

It is definitely very informative, but I wish the lectures would be more in depth in regards to the derivation and proofs.

By Ruud K

•

Feb 6, 2019

Really love the course, the quizes and programming assignments. But not 5 stars cause the audio quality is extremely poor.

By Leandro R

•

Jan 25, 2022

Very good course. It would be 5 stars if it had questions on each video and a bit more difficult programming excercises.

By Arkosnato N

•

Nov 28, 2017

course content was very good, but this course should be longer. there was a lot of material covered in a very short time.

By Michael B

•

Mar 17, 2018

More pragmatic approach with theorems would be more appealing....or maybe it is me as i'd prefer Java (DL4J)...not sure

By Santiago F V

•

Jul 2, 2020

The theorical part is perfectly explained. However, the program assingment of the las week is not as good as expected.

By Nguyá»…n Q T

•

Jun 21, 2020

Thanks a lot for clearly explaining of intuition about algorithms and optimizer. More ever, great design of assignment

By Avinash V

•

May 4, 2020

Outstanding material. Would like to thanks Mr. Andrew Ng Sir for providing such a nice and detailed description.

THANKS

By Vivi M

•

Oct 29, 2017

I really enjoyed the classes, in the training I would've liked to try and improve the model with all the tools learned

By Amit J

•

Nov 22, 2019

Great practical insights.

I wish there were programming assignments on "Hyperparameter tuning" and "Batch norm" too.

By Christopher S

•

Oct 25, 2019

Good intro to the available tools. Very guided course. For concepts to really stick, own projects or courses needed.

By George L

•

Oct 24, 2018

it's good, but definitely not as good as the first course since Prof. Ng was not very clear on some of the concepts.

By Ruixin Y

•

Apr 30, 2018

The course itself is great, but the notebook (programming assignment system) is not stable, it's annoying sometimes.

By Péter T

•

Apr 17, 2018

Useful information, good intuition, but lack of formal results. More homework would improve the learning experience.

By Ashutosh P

•

Apr 4, 2018

It was a great course. Really well taught by Professor Andrew Ng. Some "from the scratch" coding assignments needed.

By Suresh D

•

Feb 28, 2018

I hated the tensorflow part though. Would have much preferred it if we could have moved away from jupyter notebooks.

By Francisco C

•

Jul 24, 2018

Very good content overall. Very well explained and good examples. Many mistakes in the comments in the assignments.