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
62,825 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.

JS

Apr 4, 2021

Fantastic course and although it guides you through the course (and may feel less challenging to some) it provides all the building blocks for you to latter apply them to your own interesting project.

Filter by:

551 - 575 of 7,216 Reviews for Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization

By Eymard P

•

Jul 16, 2018

Very well explained and detailed. The less positive aspect is that I think the programming assignements are a bit too easy. But for the rest it's perfect, it's always interesting and clear. Thank you for the high quality content !

By Adikwu U S

•

May 31, 2020

Prof. Andrew did justice to the topic. The course contents are very insightful with respect to how the choice of parameters initialization and optimization techniques could influence the overall outcome of a Neural Network model.

By Bharath K

•

Sep 28, 2017

Nuts & Bolts of deep learning were very well explained thought in this course which will be very useful in building a robust neural networks. Maths behind the concepts were explained clearly. Thank you very much Prof.Andrew Ng !

By Rizal m M P

•

Oct 6, 2022

An amazing course that talk about hyper parameter tuning, regularization and optimization of Aritificial Neural Networks. Andew's practical advice about these subjects are really helpful, when we perform these tasks on our own.

By Jingying W

•

Jul 14, 2020

This course really helps me understand different optimization functions, regularization and dropout these valuable tools in depth. Implementing Adam and Momentum more or less from scratch makes me feel more familiar with them ;)

By Ganesh S

•

Jun 21, 2020

Great next step to the First Course. The jump into Tensor Flow was a little sudden and maybe we could've had some more smaller exercises mimicking other problems in Tensorflow before the new one came up for the final assignment.

By Carlos A F

•

Mar 19, 2020

The main advantage of this course is the amazing capacity of professor Andrew Ng to facilitate the understanding of key concepts on Deep Neural Networks. The assignments help a lot to improve the comprehension of the concepts.

By Jinxiang R

•

May 19, 2019

I am so grateful that Andrew and his team provide such great course, after completed the course now I have more understanding about different optimizer and regularization methods of the NN. And practical exercise with tensorflow

By Rahul v

•

Sep 4, 2018

This course is awesome. In the end of this I can understand the how to make your model more efficient and optimal. How I can play with our training set and how to improve the our Deep Neural Network.

Thank you so much Andrew sir.

By Ai-sawan J

•

Apr 2, 2018

I like the way Prof. Andrew explains intuitions and how Momentum works in Deep Learning. Also, this course gives practical explanations of how improve models. I would recommend to anyone who want to start learning Deep Learning!

By Dixant M

•

Oct 6, 2017

All the techniques taught were very effective. Before this course, I made a NN without knowing these techniques and it was a pain to get it to converge. Hopefully, after applying these techniques. it is performing very well now.

By Anurag D

•

Jun 24, 2021

This course is excellent to get a start of deeplearning.

I really emphasize this.

Dr. Ng is an awesome professor who can simplify abstract and complex concepts to a really linear knowledge flow i.e. removed activation layer hahha

By Ramin N

•

Oct 11, 2020

This course was very valuable and informative, and I wanna say a special thanks to Dr. Andrew NG, a great professor. Thank you very much, and finally thanks to the Coursera for giving me the opportunity of learning this course.

By HE Y

•

Jun 14, 2020

This course gives me a comprehensible insight into the tuning of hyperparameters in the Deep Learning. It gives me a better understanding by some useful and practical exercises. I really want to say thanks your efforts, Andrew.

By Zongyi G

•

May 16, 2020

I wish there are exercises for coding back-propagation on Batch-normalization and multinomial logistic regression from scratch (using python and NumPy only). That would help to deepen my understanding of those concepts greatly.

By Steve A

•

May 25, 2018

Good stuff. All in all well worth the few weeks to get a better idea of how to thing and deal with parameters.

I feel like I need a real course on tensorflow though. Documentation and tutorials are not googles strong point.

By Travis J

•

Mar 19, 2018

Very rich with information on various ways Neural Network training can benefit from optimizations. I'm sure there are many more optimizations to explore, and this serves as a great introduction to some of the more common ones.

By Daniel D

•

Sep 3, 2017

The optimization algorithms and the the introduction to tensorflow were the topics I liked the most. Although hyperparameter tuning is important, this seems to me to be still very empirical. Also, more interviews would be nice.

By Alvin A

•

Aug 23, 2017

In this course, Professor Ng shares great guidelines on tuning deep learning hyperparameters, which are a lot compared to other machine learning algorithms. This will surely help any deep learning projects to be more effective.

By Fabian d A G

•

Jul 31, 2021

The material is definitely not easy and may require a certain amount of self-study for mastery. But the lectures as well as the Discourse resources are more than sufficient to provide any additional resources needed, however.

By Simon T

•

Apr 4, 2021

Good course to teach you more about how to optimise your neural network, to speed up training, dealing with overfitting etc. This course assumes you know the basics i.e. done the first part of the Deep Learning Specialization.

By Amrith N

•

Oct 31, 2020

Got many ideas on how to increase the accuracy of the model. Introduction to tensorflow was much essential instead of programming all the stuff from the scratch. Now I am much more encouraged to learn more about tensorflow : )

By ruben y q

•

Apr 9, 2020

Excelente material, muy pertinente todos los temas del curso. Hay un error en la forma de calificar el examen de la segunda semana.

Por mejorar: Ojalá los cursos dieran las diapositivas que usa Andrew Ng para dictar las clases.

By Ferdi A

•

Jan 16, 2020

Adjusting parameters are highly essential skills for deep learning programming that most of my friends lacking. Great lectures and assignments around the topic, many thanks to the lecturer and assistants for their great works.

By dhatri P

•

Jan 7, 2020

The course will make all concepts about improving deep neural network understand in excellent manner by Andrew Ng.Must complete the course on deeplearning.ai.Mathematical concepts along with applciaitons are clearly explained.