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:

501 - 525 of 7,216 Reviews for Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization

By Kunjin C

•

Sep 3, 2017

Very practical course for implementing deep neural networks from scratch. The ideas of hyper-parameter tuning, regularization and optimization are very refreshing even for experienced deep learning engineers. Learned a lot from this course.

By Vihanga J

•

May 16, 2021

The course was really interesting and helpful! This series of coursers guides even a novice to the field through a simple, easily understandable learning process. Many thanks to Coursera, DeepLearning.Ai, and the lecturers for this series.

By Pratyush S

•

Aug 28, 2017

Continuing the trend of magnificent course content, Dr. Andrew Ng walks us through some exceptional practical advice in implementing DL algorithms, detailing the concepts and the best-practices, and mentioning the pitfalls. Simple awesome!

By Dragos R

•

Jul 17, 2019

It's a very good course for those willing to dig into the nitpicking of it. If you're really serious about this field, or if you're going to use neural networks often in your job, these lectures (and notebooks) can save you a lot of time.

By Neil O

•

Jan 12, 2018

This is an excellent class for understanding how to tune neural networks. I guess this will continue to be a valuable skill set until we have neural networks that can figure out optimal parameters to design and tune other neural networks.

By serge

•

Sep 10, 2017

I've worked with deep neural networks before for a while, but this course gave me a lot of new ideas, especially different tips and tricks on fine-tuning hyperparameters and speeding up the training of a deep neural net. Highly recommend!

By Ernest W

•

Jun 30, 2021

The course is okay. The programming assignments really shows how tuning the equations improve neural network. At the end there is a quick introduction to Tensorflow. It's too shallow but I guess rest of specialization will teach me more.

By Aminur R A

•

Mar 3, 2021

Pretty much helpful. I was a novice and this course helped me a lot to start my jourmey in a right way. I will recommend others to come and join this course and hopefully you all can get more insights in your career in machine learning.

By Wong X Y

•

Feb 28, 2021

This course provides a lot of insights towards improving performance and accuracy of deep NN with clear teaching, step by step and practical assignments. Love the introduction of TensorFlow in this course. Hats off and thank you so much!

By Carlos A L P

•

Jan 4, 2021

Great continuation of the 1st course of Neural Networks where you explore more about NN and how to optimize the implementations / algorithms. This course explains again at a lower level grade how the hyperparameters affect the algorithms

By Federico E T

•

Dec 30, 2020

The introduction to Tensorflow and real tools to work with these complex aproaches is something I did not expect and is really good. It more accessible than the previous one ! And that makes it more applicable. I am happy with the course

By Kiet P

•

Jun 28, 2020

Tuning is very important piece in DL. Thanks for this awesome course prof Andrew! A little peak into Tensorflow is quite eye-opening. Though it's only Tensorflow 1.0 but you will come to know later how powerful Tensorflow 2.0 has become.

By Michail T

•

Aug 27, 2018

This part is one of the most important to working with NN or DL nets. The instructor has achieved to teach a not so easy topic in an awesome manner so everyone is able to tune his networks as a professional. Can't wait for the next part.

By Adrian L

•

Nov 25, 2017

I this course I learned how to improve Deep Neural Networks by applying different methods that help to speed up the convergence and to reduce overfitting. Also, now I have some basic knowledge about using TensorFlow. Thank you very much!

By Hussein J

•

Dec 8, 2021

Exceptional Course. I really enjoyed the explanation of Hyperparameters. Every tip, every piece of advice helped me to build better models. Moreover, I liked the introduction part of the TensorFlow framework. Thank you, Prof. Andrew Ng.

By CLAUDIO A

•

Jul 24, 2019

pretty good course all in all !, I would say considering the difficulty of this topics, the instructor has done a great job in transmitting the relevant parts that one needs to remember and also in justifying why things are as they are.

By Alexandre R

•

Dec 29, 2018

Very well structured class as a follow-up to the first one. Heavy on information but this is a good thing. As someone who isn't pro at Python, the development part was much smoother since programming wise it is similar to the first one.

By Santiago I C

•

Dec 5, 2018

En línea con los anteriores. Muy teórico pero perfecto para entender los entresijos del funcionamiento de los algoritmos. Si acaso echo en falta algo más de tensorflow pero supongo que se verá en el resto de cursos de la especializacion

By Rahul Y

•

Nov 18, 2018

I really like the practical aspects of the course where although there is a focus on teaching the fundamentals, there is also a good focus on teaching the latest frameworks to apply the knowledge of the learnt concepts more efficiently.

By stewart n

•

Feb 24, 2018

Excellent practical advice on running NNs. The lectures teach the subject matter in a lucid and intuitive way. The course ends with a TemperFlow exercise that shows how to implement NNs at a higher level than peviously shown with numpy.

By Alejandro M

•

Nov 12, 2017

Great material. Short, precise videos.

It would be great if you propose projects to work on outside the course, in order to learn more about the topics. Just like ideas where we could apply what we have learned and a seed to build upon.

By Jagdeep S

•

Oct 29, 2017

Loved the programming assignments. After learning Tensor flow in this course, I learnt about Keras on my own. It made model building very easy, but without understanding the basics, going straight to Keras would make a person dangerous.

By Carlson O

•

Oct 1, 2017

Again, the course was great. Covering a large spectrum of deep neural net adaptations and configurations of its hyperparameters give me a better understanding and tips with how to best use this deep learning technology. Congratulations!

By George M

•

May 15, 2021

Very good and interesting course!

Programming assignments were a bit easy, but it does not bother me as this is not an "introduction to programming" course. The point is to get the basic ideas of programming these kinds of applications.

By Hemanth R

•

Aug 19, 2020

Absolutely loved the course. have learnt the basic pillars of Neural Networks and DNN. Andrew has clearly explained the diagnosis of a problem and identify bias and variance. then Regularisation techniques, Optimisation algorithms etc.