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
63,243 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

HD

Dec 5, 2019

I enjoyed it, it is really helpful, id like to have the oportunity to implement all these deeply in a real example.

the only thing i didn't have completely clear is the barch norm, it is so confuse

Filter by:

6626 - 6650 of 7,261 Reviews for Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization

By Alexey V

•

Mar 18, 2019

Ran into bugs with some assignments, for example week 7 was not correctly calculating final model

By Tamás J

•

Jun 14, 2018

Jupiter Notebook fails too offen! I had to close the window, start again, which is very annoying!

By Chen X

•

Mar 27, 2018

It's fun they assume you know human error rate or optimal Bayesian. It's very rare in real world.

By Alejandro R

•

Oct 26, 2017

I miss the end of video quizzes, but can't rate it lower than 4 because this course is excellent.

By Prasad D

•

Jul 1, 2020

Some examples to be solved manually would have helped get a better understanding of the concepts

By Ayushman K

•

Apr 24, 2020

Learnt a lot of new things. Only complain i have frmo this course is the use of Tensorflow 1.x .

By Digvijay R

•

Jan 18, 2020

perhaps more practice of tensorflow is required. The tensorflow module also needs to be updated.

By Isaraparb L

•

Jul 15, 2018

Some of the math may be hard to grasp, but the course gives a lot of useful information overall.

By Amine B

•

Apr 25, 2018

Great course, very complete and instructive! The programming exercices should yet be less guided

By Shobhit K

•

Aug 7, 2022

I felt Tensorflow coverage was fairly limited and more practice of Tensorflow would have helped

By Yasod S G

•

Aug 3, 2020

It is better if you can provide some proper documentation for the TensorFlow coding. (syntaxes)

By mandar k

•

Jul 29, 2020

Great course, learned about different hyperparameter in neural networks and their optimization.

By sathwik m

•

May 9, 2020

It was a great course.

I hope we are going much "deeper" in deep learning in the next courses !

By Sebastian R C

•

Mar 22, 2018

I think the material is quite basic, since it is an specialization, we could go a little deeper

By Ashish C

•

Jun 25, 2021

week 3 was quiet tedious and a more explanation about tenser flow would have been more useful.

By Nabham G

•

May 22, 2020

Deep learning is so Deep X'D. I got to learn so many new stuff which I wasn't aware of before.

By SHAHAPURKAR S M

•

May 20, 2020

The batch normalization part needs to be more comprehensive. Else, everything is just superb !

By Dongjin K

•

May 19, 2020

Hope to see the course materials and assignments get updated for tensorflow 2.0 in the future!

By Kasper J

•

Oct 1, 2017

Overall a very good course. However, I was hoping for more material on programming frameworks.

By Gleb F

•

Nov 8, 2020

Programming assignments are too easy, and don't help to grasp and think through the material.

By Shruti S M

•

Jun 5, 2020

Some more details & programming exercises about batch normalization could have been provided.

By Sanket D

•

Jun 5, 2020

It could be updated to include more of the newer optimizations such as Bayesian optimization.

By Hakob J

•

Oct 11, 2017

It is very helpful course both for theoretical and practical aspects of Hyperparameter tuning

By Juan A M C

•

Jan 15, 2021

Me llevo un tiempo, pero lo logre. Ahora a jugar con algunos datos y mejorar los resultados.

By manpreet s

•

Oct 3, 2018

good course, easy to understand and very nicely explained concepts about the neural networks