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.

XG

Invalid date

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:

6551 - 6575 of 7,238 Reviews for Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization

By Arun J

•

Sep 16, 2017

really loved the course material but would have loved it more if it gave more in depth tutorials on tensorflow

By Hector D M P

•

Sep 2, 2017

Nice and clean; with nice focus in the framework; but they also could be more in depth regarding the exercises

By Crack I

•

Jan 20, 2024

Great course by Andrew. The exposure and the length of what I had to learn changed the circuitry of my brain.

By Samuel C

•

Sep 27, 2021

Some of the programming exercises weren't as polished as part 1 of this specialization. Still great overall!

By Shailesh

•

Apr 3, 2020

Really helpful in terms of practical application and tricks/tuning for DNN. Also starts on TF which is bonus!

By Ramanjee M

•

Aug 20, 2017

Quizes as part of middle of lectures help to check the understandings. For many lectures quizzes are missing.

By Pabbisetty S R

•

Jul 5, 2020

explanation is very good but assignments need to be done comletely by student not like filling missing parts

By Rohit G

•

Mar 26, 2020

The tensorflow portions need to be updated. Otherwise it's a great module, building on the previous courses.

By Ryota M

•

Mar 21, 2018

-1 : Serveral bugs inside the assignments, causing 0 grades in auto grader

That said, a perfect intro to DNN.

By Qihong L

•

Oct 1, 2018

sometimes the teacher speaks too fast to follow, but the content itself is very good and easy to understand

By Donguk L

•

Nov 25, 2017

Maybe providing some video or reading resource for back propagation processes for batch norm would be good?

By Snehitha D

•

Jun 20, 2024

the concepts are a little complex and tricky and i hope there's a project by the end of the specialization

By Mozhdeh S

•

Mar 21, 2022

I needed more foundation for understanding tensorflow programming. However, I learnt a lot in this course.

By Parjanya P P

•

Jun 23, 2020

The answer in the last assignment was wrong, wasting a lot of my time. But otherwise the course was great.

By Aaron E

•

May 4, 2019

its a good intro, if not a little simplistic with the coding exercises, bring back the quizzes mid lecture

By Alex S

•

Dec 11, 2018

A small validation output error that is still not fixed prevent to rate all stars for the exellent course.

By 苑思域

•

Aug 3, 2018

This one is actually a little bit better than the first one, maybe less content, maybe more understandable

By Leitner C S E S

•

Aug 29, 2017

Excellent course. But -1 for using TensorFlow, a not-really-free framework, to introduce students to them.

By Jayshree R

•

Jul 4, 2019

An intuitive approach towards Hyper parameters. Covers the concept of optimization algorithms quiet well.

By Makragić A

•

Jan 9, 2019

Great lectures, I'm little disappointed with TensorFlow tutorial, there should be 1 week for that only...

By Richard H

•

Sep 28, 2017

Fills in the tricky gaps in using DNN that are necessary to transition from basics to practical projects.

By Harry L

•

Mar 21, 2020

Too much code is given, which makes the programming assignments too easy. The material is great, though.

By Shijian G

•

Nov 29, 2019

These series are generally clear and well-organized. It would be better to provide tensorflow materials.

By Kevin T

•

Mar 29, 2023

The assignments could have been explained a little bit better. The course was overall very interesting.