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:

976 - 1000 of 7,238 Reviews for Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization

By Andrew C

Jan 23, 2020

This might not be the best curse . in the world, but it is doubtlessly the best one in my mind. Thank you, Dr. Andrew! Thank you, Coursera! Also, many thanks to Github!

By Sebastian R G

Feb 26, 2019

Este segundo curso de la especialización fue realmente provechoso. Muchos de los conceptos que se manejan resultan vitales para lograr desarrollar buenos modelos de AI.

By Damianos M

Jan 25, 2019

Again, a very structured course with Dr. Andrew Ng being so calm and simple explaining all methods of the course. It was worth my time! Many thanks to the organizers :)

By Kazuki Y

Jul 1, 2018

Very nice materials. The self-contained Jupyter Notebook is nice in that it doesn't require local installation. However, it kept crashing. I'd much rather code locally.

By Muhammad S

Apr 17, 2018

Today i have finished the 2nd course. It was amazing a lot of things to learn and still looking for the remain 3 courses of deeplearning.ai. Thanks to the coursera team

By Rishikesh B

Sep 5, 2020

The challenging concepts therein the course were well-explained & simplified. Also the Assignments gave a decent chance to brush up the concepts learnt while lectures.

By Tarique S A

Aug 17, 2020

Leaned how to tune the required parameters and hyperparameters in different scenarios which is a big help. Hope to implement the learning and continue to third course.

By Pratama A A

May 31, 2020

Andrew Ng is the best for explaining "What 's going on" on every single lecture,if you didn't understand ,search it ,it will help you to survive :D,Enroll THiS CoUrSe

By 谢宁翔

Apr 6, 2020

Extremely nice the course, very useful and easy to master. Only thing is that the model of the final work is really not good enough. I tested five gestures, all wrong.

By Priya K

Apr 2, 2020

The course helped me gain a clear perspective on how to make my Deep learning model improve in performance and accuracy. The teaching was clear and precise. Thank you!

By Gorden J

Feb 29, 2020

Really great introduction to deep learning. Made the use of frameworks such as Tensorflow easy to understand through guided implementation of deep learning using Numpy

By Iuliia M

Aug 23, 2019

It course contains best opportunities to learn how work with your Neural Network and how to adjust parameters. So far, this is my favorite part of this specialization.

By Cary M C

Jul 16, 2019

Really impressed with this course....Andrew is one of the best teachers I've ever had and his Deep Learning course is one of the best courses I've taken from Coursera!

By min x

May 18, 2019

This course is helpful because they taught the fundamentals and the intuition that goes behind tuning methodologies instead of going straight to the technical portion.

By Dawid D

Aug 8, 2018

Great course! The only little thing was that submission grades of one assignment were broken and few things could be polished in this course. But overall it was great.

By Christopher O

Feb 25, 2018

Really nice to go into the basics of some of the most used optimizers and regularizers currently being used. Also nice to have an intro into the basics of TensorFlow.

By Bruno L

Sep 12, 2017

Excellent course with great learning materials and tests. The sample code provided in the programming assignments is a great starting point to amazing implementations!

By Kamesh D

Oct 8, 2023

I knew all of these but the detail and why it was needed is not explained in most places. This specialization is best place to get the holistic view of deep learning.

By Chandan D

Jun 26, 2021

Amazing course to understand verious concept of Hyperparameter tuning and optimization. Regularization concepts are very well explained and helped me to learn a lot!!

By Sreenivas K

Jul 9, 2020

Very well taught by making simple explanations for various complex algorithms. Hope Tensorflow was taught more deeply as only the surface of it has been taught here .

By David C

May 6, 2020

Very recommended, even though the exercises can be passed without really understanding, they are very well explained and if you want to, you can learn lots from them.

By prashant p

Jan 23, 2020

The course content is of adequate depth and sets a good base for us to start applying DL in our projects. A project component can also be added to make it even better

By Devkul S

Jul 2, 2019

This is the most important course to know in details about hyperparameters, epochs, regularization and opitmization. This course taught me in deep about improving DNN

By Michael R

Mar 10, 2018

Continues right where the first module stopped. Really like the sessions approach and the exercises and quizzes are well documented to serve as future 'cheat sheets'.