# Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization

FREE

**#17**in category Machine Learning

This course will teach you the “magic” of getting deep learning to work well. Rather than the deep learning process being a black box, you will understand what drives performance, and be able to more systematically get good results. You will also learn TensorFlow. After 3 weeks, you will: – Understand industry best–practices for building deep learning applications. – Be able to effectively use the common neural network “tricks”, including initialization, L2 and dropout regularization, Batch normalization, gradient checking, – Be able to implement and apply a variety of optimization algorithms, such as mini–batch gradient descent, Momentum, RMSprop and Adam, and check for their convergence. – Understand new best–practices for the deep learning era of how to set up train/dev/test sets and analyze bias/variance – Be able to implement a neural network in TensorFlow. This is the second course of the Deep Learning Specialization. deeplearning.ai is Andrew Ng’s new venture which amongst others, strives for providing comprehensive AI education beyond borders.

## Instructor Details

**Andrew Ng**

Courses : 4

## Specification: Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization

Duration | 15 hours |
---|---|

Year | 2017 |

Level | Beginner |

Certificate | Yes |

Quizzes | Yes |

## 143 reviews for Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization

### Add a review Cancel reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.

FREE

Manish C–Like all other andrew ng courses this course is also the best course to deep dive into neural network algorithms .

Zhuo C–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!

Prashant P–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

Md F I–Great experience!

heykel–Absolutely helpful for Newbies to Coding and Machine Learning. It gives a great intuition also for managers, who are typically useless in coding…

Janis R–Nice intro to TensorFlow, thanks!

ngoy m–Learning quickly from very well thought out and put together lectures by Prof. Ng and team

Ridvan B–The teacher is awesome and if you are interested in that topic, this course is just perfect.

Nicolas L–programming assignment should be more open, with less guidance

Hideyuki K–Very nice course since it contains “real–world” examples.

Tanay G–This course taught me a lot of new concepts and tricks to speed up the training process as well as ways to reduce overfitting and biasing in a neural network. I would’ve liked the course even more if the instructors took a deeper dive in frameworks.

Karan A–Notebooks didn’t work properly

yangyandi–It’s a very useful course for me to have a better understanding of hyperparameter in neural network.

Sathiya N C–a very good course to get started with hands–on deep learning. This will not only cover the hyperparameters and optimization techniques but also covers the underlying math and reasoning behind using it. It’s fun! Go for it!

AhmedAbdel–Aal–it was great course, what i learned was very useful in a very good way of teaching. thanks Coursera and thanks Andrew Ng

AhmedAbdel Aal–it was great course, what i learned was very useful in a very good way of teaching. thanks Coursera and thanks Andrew Ng

Piyush K B–Great teaching by Andrew Ng. Learnt a lot and I feel confident to implement it.

Ashwin A R–This course helped in deepening knowledge about optimization techniques and how they could make ML/DL algorithms robust while training. This also provides a good introduction to the Tensor flow framework.

Juan P A A–The contents are actually good, and it doesn’t require a very extensive prior knowledge, so it’s even suitable for people with little experience in programming or math. However, despite being a course that has been out for over 2 years, there are still some subtitle issues (in English), and typos on a clarification slide.

George–the course was very intuitive, even for some who didnt have any robust computational algebra

Murtaza V–Great Learning Experience

Akilu R M–Great, well organised, student–centred course.

AKSHAY K C–Great follow–up course by the instructor after the Neural Networks Course. Got an in–depth understanding of hyperparameter, regularization, and optimization. Kudos to the team for designing such a good course.

Avishek S–Good learning!

pranav b–Best Course For Learning Hyper parameters Tuning

Fabrice H T–Super!!!

Muhammad T B–very wonderful course for Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization

Sreenivas N M–Excellent second course that backs up the first course in tuning.

Abdul M–math part was quite difficult to understand

Neelesh A–Absolutely elegantly done by Prof. Andrew Ng. Have become a Deep Learning addict, thanks to the professor. Eagerly looking forward to the next one!

Abdelrahman R–Thanks

Jairo J P H–El curso es muy bueno, particularmente estoy muy agradecido con COURSERA, por darme la oportunidad de hacer los cinco cursos de la Especializacion en Deep Learning con ayuda economica y permitirme tener acceso a este tipo de capacitacion y certificacion. Muchas Gracias&! The course is very good, particularly I am very grateful to COURSERA, for giving me the opportunity to do the five courses of the Deep Learning Specialization with financial aid and allowing me to have access to this type of training and certification. Thank you very much!

Raju L–I am really grateful to the deeplearning.ai community and Coursera for providing such an amazing platform to learn and grow. undoubtedly, one of the best courses for learning deep neural networks.

venkatesh–Definitely 5 star ..This teaching is cake walk for newbies and concepts explained very well.

Wooshik K–Thank you very much for giving me an opportunity to learn every aspect of deep learning so easily.

Jose A F R–Un curso muy bueno, el instructor tiene dominio del tema y sobre todo el final del curso es muy bueno en cuestion de poner en practica la teoria que al principio te explica. En ocasiones el instructor va un poco rapido en los terminos teoricos y puede llegar a abrumarte. Creo queria ideal poner mas ejemplos practicos cada que explica un concepto.

Abdallah D–Fantastic course providing a broad overview of hyperparameter tuning in deep neural networks. The introduction on TensorFlow is informative. Looking forward to the three remaining courses of this great specialization on machine leaning. Thanks Andrew and their assistants for putting those courses together!

Dipanjan G–This again is an excellent insight on the hyper parameters and deep learning frameworks. The extreme prowess in the subject but at the same time a very lucid and relaxed style of teaching from Andrew helps quickly grasp these difficult concepts. Looking forward to much more!!!

Karandeep–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.

Ratnakar–Glad to have done this course.

Jun–very clear explaination

Yuanxin L–Very good!

MAYANK A–Please provide slides at the end of whole course

Dweep J–Very well taught!!!

Vishakha S–I think a short video on tensorflow might help the learners

Himanshu G–very insightful and developed intuition

Anand K–The insights provided by Prof. Andrew are priceless. I sincerely hope that I get to go in such depths, as taught by him while implementing these algorithms in real–world applications.

Prashant M–A very nice course explaining the details of hyperparameter tuning. Thanks to Coursera and Andrew Sir for such a wonderful course.

Muhammad w–I was a great learning experience thanks team and specially Andrew

Nikhil N–Amazing course! Really helped me to understand the intricacies behind neural network workings and how to exploit them to improve performance.

Deep G–Amazing content!

jarat m–just amazing

Saurabh K M–The course is awesome…..literally speaking… awesome…!!

Marshall–Great overview with good practice problems. I never felt overwhelmed during the class.

Goda D R–The video content is very good to get a good hang of theoretical aspects but the programming assignments are too spoon fed because of which after doing filling the blanks, you don’t feel confident enough to implement the same on your own. Instead the assignments should be changed to cases where instructions are given in words and entire function should be implemented by students.

Mohamed A B–More tensorFlow would be nice, great course honestly great work on intutions

Juncheol Y–^^

Abhishek–Amazing course, helped me with introduction to Tensorflow

Mariola N–Excellent course and very useful introduction to Tensorflow.

Prashant A–Very good instruction

Erik H–Learnt a lot re: tuning of hyperparams, optimization algos, and tensorflow.

Ignacio H M–I enrolled in this course without taking the previous ones (I have already done an MSc in Computer Vision and Machine Learning so I thought I wouldn’t need the others), but the material has been easy to follow and understand. It is really interesting as it helps you understand important concepts such as bias and variance, or why does batch normalisation work. Sometimes Deep Learning can be seen more as an art than a science, and this course is helpful for defining a good strategy when carrying out deep learing experiments.

Rocco I–Good course, as the previous ones. I wish we had the possibility to download the slides or get some summary notes… Going back to the videos to check some infos is not handy.

John G–Great overview of optimizing networks and intro to tensorflow.

Xiangyu P–Very clear explanation. Carefully designed practices. Wonderful Course!

Abhishek S–very helpful must join and do all questions !

Jordi A C–Very nice and well explained continuation to course 1. Very usefull tools to optimize results.

Kingsley N K K–Good guideline and full of useful information.!

Rajesh R–Great courser to study and practise. Highly recommend it.

M A–As a 2 3yrs experienced deep learning developer should say that this specialization is awesome specifically this course, it’s really practical every day to get a better result just tune the parameters as you’ve learned in the course and boom that’s it you get a better model. Thanks

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

William–This is everything I am looking for. Step by step basic AI. I have already taken a couple other AI specializations but I wanted to step back and really understand the basics.

Manish.M–Really informative course to learn about the various kinds of optimizations and the differences between the optimization techniques. Learnt how to tune the hyper parameters for effective training . Also got a chance to learn about mini batches and the corresponding gradient descent and the difference between batch and mini batch gradient descent.

Ritik G–The course is good and teach very high level concepts very easily.

jagrati s–For a busy mom of 2, 42 year old, senior executive., this course is best optimize for the pockets of time I get. Concepts are explained very clearly, and course is well paced

Dhruv P–WOW, Vet insightful

S A–An amazing course. Can’t wait to explore the other courses under this specialization

Hugues D S–Great insight on “rare” local optima in high dimensional spaces.

Arun G–Excellent course, giving a very good insight into how to approach building a deep neural network, the concepts of various parameters, tips on how to best achieve a good algorithm and a step by step walk through of the different algorithms, parameters and optimization.

Mert C–Perfect. Golden quality. Thanks to Andrew Ng.

Aditya K–Everything till now was good, But I can’t tell why my forward propagation method is rejected although it matches the expected output. So my marks were deducted for it without any reasonable explanation.

santosh–Excellent course. Bit tougher than first course

Snow H–Really helpful for me

Haziqa S–Wonderful

Tohid S–This course was amazing. I am speechless about how Andrew presented the materials. I enjoyed every minute of it!

Shawn B–great!

Francesco C–The part on optimization algorithms is really great!

Okta F S–I’m very happy can finish this course. After taking this course, I understand how to optimize deep learning model, how to tuning hyperparameters. Also, by doing the programming assignment I can understand how to do optimization process from scratch

Surga K G–Really good and clear explanation of concepts and thanks to Andrew NG sir

Yanto J–Thanks to Prof Andrew, now I can understand the roles of hyperparameters. Tuning them skillfully requires a lot of experience, though.

MD S A–Great insight into deeper concepts of deep learning. Lectures on different optimizers very helpful in understanding the basic concepts. Introduction of Tensorflow is great.

Bhanuprakash B–Best course to get clear with concepts of Deep Learning.

Alexander S–Very good overall, exercises could be a bit more free

Juan B T G–This course, as part of Deep Learning specialization, is simply great.

PRIYANSH K–nice course and very helpful

Lei Y–Always excellent!

Justin G–A good step up of difficulty from the first course, I’m going to finish this Specialization

Boris B–Informative overview about ML techniques which are helping on the way to improve modelling with deep learning.

MANOJ K–Great content for beginners and concept focused.

David F–Excellent course. Helper code still feels a little too much.

Disheng M–Tensorflow is kind of outdated, hard to find documentation

Nilesh S–Best Course

Mohammad S I–I am really glad to learn the tuning and optimization techniques. Hopefully, I can implement them whenever I need. Learning a new framework (TensorFlow) and using it to ease up the bigger calculations was the best thing about the course. Hats off to Andrew NG for designing a course like that.

naren–Thank you so much for preparing such a good content!

Jag S S–Tensorflow Version used in last assignment is old and syntax has been changed in tensorflow 2.0, it should be updated. But Overall very knowledgeable and insightful course.

Zachary Z–Learned a lot about tuning and different frameworks. Definitely math intensive and more of a brief overview than a deep dive of these techniques and tools.

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

Shyam P–This is the best course ever on hyperparameter tuning and regularization as well as optimization. A big thanks to Andrew Ng sir and his team.

prateek l–There should be more examples first of all then moving to mathematics.

Maxime C–Really good course. This incrementation of difficulty while reusing previous courses is perfectly working

Saurabh M–I’ve done courses with similar content but no other teacher could explain it like Andre Ng. It is really a course you must do if you’ve completed the intro course

Mohammad J P–Great!

Jeffrey B–Another great course! Can’t wait for the next one!

Rafael R–Muito bom

Akash D–Thank You! Sir

Adrian M–Appreciate so much more the core essentials of applying common optimizations to NN models.

Dingduo Z–Able to follow and understand root cause

Santosh M–Excellent course

KISHOR–i learnt a lot about tuning Neural Networks through various optimization and regularization methods in this course. this helped me a lot in understanding the working and derivatives of optimizing neural networks through various algorithms. this course is making the foundations of deep learning look easy and understandable than other sources to the person who is taking up this course.

Zhao Z–The course is easy to understand, and the assignment design is very thoughtful. Many parts that do not matter much with key knowledge have already been completed for us, which significantly improves our learning efficiency

Divy D–I have done two courses under Andrew ng and I am grateful to Coursera for their highly optimised and easily learning course structure. It has greatly help me gain confidence in this field. Thank you.

Paraskevas P–More practical examples would be very useful.

Prateek S–Great course. Covered most of the optimization techniques.

Mohammad a–Great Course (y)

Tolga–Great course. You learn a lot on optimization and normalization techniques and tensorflow.

Deepak S M–This course has valuable content! Well satisfied. ðŸ™‚

Purushothaman S–Wonderful course!!!!!

Zhe W–Very detailed so it is not hard to follow. Professor really put his heart and effort on this course. Thanks!

Muhammad A k–5/5.Thank you sir for helping me in my career.I recommend everyone to go through this course if you really want to learn detail about hyper parameter tuning , optimizers and regularization used to make neural network better. It helps to open black box of Neural network and know in detail about how all works.

Naveen S P–It’s Excellent experience !!!

Mehedi S–Beautifully organized

Uday N–Excellent Course

Thomas P–Some more basics on tensorflow would have been great!

Sajib K S J–I am lucky enough to get financial aid. Thank u courSera..Thanks a lot.. NG Sir is a masterclass..

sudheer k–great teaching in an easier approach. Thanks Andrew ðŸ™‚

farhad–Well organized and good assignment materials

Rahul K–Andrew NG in Machine and Deep Learning is like Bruce Lee in Martial Arts. Starting from class 1, he covered each and every small topic and correlated those beautifully. Feels lucky to attend this course. Highly Recommended!

Shiyang F–Great

Aleksander L–I’m not sure if those technics are still applicable with high level libraries, but I really like the way Prof. Ng explains it and it helps me to better understand how it works behind the scenes of already written functions

Nick M–really clear and well paced

Bkash T–Learned a lot of interesting stuff to improve the speed and efficiency of the model. Moreover, the introduction to the TensorFlow framework was intuitive.

Shantanu M–best to understand the internal working of neural networks and different parameter tunning to make their functioning faster and efficient

Deeplaxmi L–Thankyou for your great guidance sir. I am diploma student where we ain’t taught much maths related to ML. I found difficult to understand mathematical equations. So i request you to upload a course on that too.