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
62,882 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

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.

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

Filter by:

776 - 800 of 7,219 Reviews for Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization

By Alister M

Aug 24, 2021

I learned a lot about setting up neural networks and what to expect when setting them up. Finally I understood the importance of using Tensorflow and other environments like it moving forward.

By Dharanidaran

Feb 19, 2019

A must have course to know the effect of Hyperparameter tuning, and a great programming exercise on Tensorflow for Beginner. I highly recommend this course if you want to build accurate models

By Darshil P

Nov 7, 2018

Amazing course, well structured. Learned a lot about tuning parameters and different optimisation algorithms. Looking forward to complete specialization. Thank you Coursera and Andrew Ng Sir.

By Bernard W

Aug 18, 2018

Concise and comprehensible. A lot of ground is covered, but I found by taking notes by hand and replaying key parts of lectures, I was able to follow along and understand the course material.

By Shrey P

Jun 13, 2018

Good course. Teaches you the practical aspects of deep learning. Take everything with a grain of salt. As Dr Ng has pointed out, deep learning knowledge of domain seldom translates to another.

By Linghao L

Jan 1, 2018

Comprehensive course on deep neural net optimization skills, you will get a pretty complete understanding of how to make your nets work more efficiently and save a lot of time. Don't miss it !

By Shaoduo X

Sep 10, 2017

The last part of the tensorflow tutorial (model() function) might need more explanation on the some tensorflow internal stuff: like I have a question, how does TF store the optimal parameters?

By Li P Z

Oct 7, 2019

fantastic course, although programming assignments not as challenging as Andrew Ng's Machine Learning course, inviting experts like Yoshua Bengio to give insights is also uniquely valuable...

By CHEYU L

Jul 13, 2019

This course is really helpful for improving the structure of the nn model. The most important thing is that now I have some direction to keep learning and getting my algorithm better. Thanks~

By narendra@live.com

Jun 22, 2019

Loved everything, great course, i would have liked a bit more detail on tensor flow, but i know Prof. Ng has taken out a tensor flow course now, i plan on taking that too. Thank you Everyone!

By Alfonsus G C

Nov 9, 2018

Great course for early machine learners to gather intuition and knowledge about how the code in deep learning frameworks actually do at the lower-level, but some typos still need to be solved

By Jie Y

Dec 26, 2017

Interesting content, feel like building the deep learning/neural network bigger and more complex. Very good course series. Definitely recommend to my friends who are interested in this field.

By Zacchaeus W

Aug 20, 2017

Perfect Course! Perfect Intuition! Perfect Practical Learning! MUST TAKE!!!!

P.S: become more familiar with numpy before taking this course. Otherwise, you may not understand some of the code.

By Vincent Z

Apr 5, 2020

This course is quite helpful for me. It covers the fundamentals of neural network and tensorflow. It teaches knowledge of neural network in a systematic way and I have learned a lot from it.

By Abhishek K G

Oct 18, 2019

The course was very good to make understand the hyperparameters in the neural network and how to optimize them to produce good accuracy over the model. I have learned a lot from this course.

By Parth D

Sep 28, 2018

This course is a very well structured course of Machine learning , where all the concepts are taught right from the most fundamental principles and that makes them easy to comprehend with.

By Yong H P

Jul 25, 2018

Good summary for very basic but most important ideas/concepts of DNN. I will keep looking at it until I fully understand it.

DNN에 대한 기초적이면서도 가장 중요한 정보들을 잘 정리해 주셨습니다. 앞으로도 계속 다시 찾아와서 볼 내용들이네요.

By SALIM T

Jun 29, 2021

This second course is an amazing addition to the first one, i have to say that it set me on the right path in my Deep Learning Journey. a BIG THANKS to everyone who helped make this Course.

By Mohammad J “ S

Apr 25, 2021

This course provided me with invaluable insights into hyperparameters of a multi-layer perception and the important role their optimization plays in the performance of deep learning models.

By Ramon S

Apr 5, 2021

A really good continuation of the lessons learned in the first course, and a gentle introduction to TensorFlow. Overall a 9/10, it would be a 10/10 if the assignments were more challenging.

By Karandeep

Feb 3, 2020

Course is very good but better notes should be provided as it is a paid course. Also, it would be better if assignments are little challenging and hints shouldn't be provided at every step.

By Yingzhao L

Nov 21, 2019

Again this is another great course continuing the first course. The only thing to say is that TenorFlow assignment needs to be update to version 2 in order to benefit the simplified syntax.

By Aristotle M

Sep 11, 2019

This course was very helpful in that it delved into more of the practical aspects of building deep neural networks. It builds on the first course very well, and I would highly recommend it.

By Sumanaruban R

Oct 24, 2018

This course helps to become pro/expert in DL/ML within a short period of time. Andrew shares his decade long experiences and best practices in this course. I strongly recommend this course.

By Heyang W

Aug 16, 2017

Great hands on experience of tuning and tensorflow tutorial. Unlike the old ML course and the one taught by Hinton, this course prepare you for the newest framework instead of Octave staff.