Chevron Left
Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization に戻る による Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization の受講者のレビューおよびフィードバック



This course will teach you the "magic" of getting deep learning to work well. Rather than the deep learning process being a black box, you will understand what drives performance, and be able to more systematically get good results. You will also learn TensorFlow. After 3 weeks, you will: - Understand industry best-practices for building deep learning applications. - Be able to effectively use the common neural network "tricks", including initialization, L2 and dropout regularization, Batch normalization, gradient checking, - Be able to implement and apply a variety of optimization algorithms, such as mini-batch gradient descent, Momentum, RMSprop and Adam, and check for their convergence. - Understand new best-practices for the deep learning era of how to set up train/dev/test sets and analyze bias/variance - Be able to implement a neural network in TensorFlow. This is the second course of the Deep Learning Specialization....



Apr 19, 2020

Very good course to give you deep insight about how to enhance your algorithm and neural network and improve its accuracy. Also teaches you Tensorflow. Highly recommend especially after the 1st course


Oct 31, 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.


Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization: 5301 - 5325 / 5,690 レビュー

by samuel E

May 27, 2020

Programming assignments can be made more rigorous with more hands-on coding

by Tukaram P

May 27, 2020

everything is good, jypyter notebooks are slow gets confused in assignments

by Pranaydeep C

Apr 21, 2020

I really liked it because it made me specially under stable with Tensorflow

by Fredrik C

Jul 18, 2019

Great, but could be better. Fix the typos. Add summarized video notes. Etc.

by Saurabh D

Sep 12, 2019

Insights about how machine learning works in real life is quite ingeniuos.

by moonseok s

May 28, 2018

very good lecure.

somewhat difficult to me. I will repeat again and again.

by John F

Jan 26, 2018

Very informative but got some issues with the last programming assignment.

by Arjan H

Dec 08, 2017

More rigorous independent projects/assignments are needed for this course.

by Carol Z

Aug 19, 2017

Deepened my understanding of how to make deep neural networks work better!

by Xiaoliang L

Mar 25, 2019

Practices are more like "type after me" than a real learning opportunity.

by Jorge G P

Oct 27, 2017

Excelent course with very interesting insigth on tuning a multilayer ANN.

by Delowar S

Jun 02, 2020

this course will help me to improve my academic skill beside help future

by Shahin A

Apr 18, 2020

i rate this course 4, its really good one and learned alot in the course


Apr 25, 2019

Good can be improved by providing more code based video like Tensorflow.

by Olena I

Apr 23, 2020

I think TensorFlow is outdated, PyTorch is the way to go in the future.

by Jaap d V

Jan 07, 2020

Some tricky parts in the programming assignments. otherwise great class

by alfredo g

May 29, 2019

too math, i hope futher parts contain more implementation than calculus

by Imran P

Oct 04, 2017

I'd like a little more focus on tensorflow, perhaps starting at week 1.

by prateek l

Mar 27, 2020

There should be more examples first of all then moving to mathematics.

by Mohammad A

Feb 25, 2020

Great Explation of hyperparameter tuning and best intro to Tensorflow.

by Pascal A S

Jul 22, 2019

A bit too technical for my taste. But useful examples to work through.

by Rindra R

Oct 10, 2017

Good curriculum and to the point. TensorFlow introduced a little late.

by Ashish G

Apr 27, 2020

course is not updates to tensorflow 2 but overall it is very helpful.

by Fabio S

Nov 04, 2019

Suggestion of references, as a complement, would be very interesting.

by Marcos C D

Nov 03, 2019

Content needs update to leverage the state of the art in the subject.