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

AS

Apr 18, 2020

Very good course to give you deep insight about how to enhance your algorithm and neural network and improve its accuracy. Also teaches you Tensorflow. Highly recommend especially after the 1st course

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:

7051 - 7075 of 7,216 Reviews for Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization

By Dartois S

•

Aug 17, 2017

A bit less good than the previous course. It would have been good to have a chance to concretely implement Batch normalization. Then I think the tutorial on tensorflow needs more details and explanations of the what and why of the conventions. Anyway I was really happy to learn a bit about tensorflow, I hope I will use it more through the course.

By Ali I

•

Sep 4, 2021

this course provided me with very fair insight, however, i felt that the Tensorflow portion was covered ina hurry. I had no background of tensor flow, and I am believing that the way it is covered might be the right way and I will build up on it. Even while covering the last assignment i had not much familiarity with the syntax of tensorlfow....

By Amit C

•

Nov 20, 2019

The fact that the lectures are not available to keep is problematic. Also, the programming assignments leave too little to do. Only few lines of code, that in most cases are simply copied from the problem description. It would make sense to broaden the programming tasks, and let the students really cope with many of the real-world challenges.

By Volodymyr B

•

Sep 19, 2021

The last programming assignment in the course is a bit better than the rest, while lectures are of rather high quality. In Quizes some questions are confusing. E. g. Andrew Ng several times said that parameters should be revised from time to time, but there is a question that (in couple with correct answer) states the opposite:(

By Erick M A

•

Mar 27, 2022

Awesome content but one big flaw: After 2 months using numpy to build neural networks (since course 1 of the specialization), briefly touches TensorFlow for around 2 hours. I feel like we should at least do everything we did with numpy (l2 regularization, drop out, 2 layer nn, deep nn, etc) once again using TensorFlown

By Virgilio E

•

Nov 27, 2017

The course explains great tips for optimizing and tuning NN, bu I miss some more practical examples where observing and compare results when applying the different techniques studied.

Also I miss a general schema of all optimization and tuning tips in order to know when and where apply each depending on conditions, etc.

By Till R

•

Mar 2, 2019

Exercises are too easy, and lectures are kind of boring. The Jupyter / iPython system does not run smoothly. I ended up downloading everything on my local computer, completing the assignment there, and then pasting the code into the coursera notebook. That makes the assignments take 50% longer than necessary.

By bob n

•

Nov 15, 2020

Would have rated higher, lost 2 stars because uses Tensor version 1. Keeping courses current is very important to me. Rating 3 even that though I thoroughly enjoyed this course and learned what's under the covers in packages such as tensorflow. Not sure if there is an excuse for not updating the final lab.

By Tomer G

•

Nov 9, 2019

The content is 5 stars.

However, technicalities of assignments not getting submitted and then needing to investigate in the discussion board what others did to be able to submit an assignment..

Assignments not getting submitted&graded is a criticial bug, that's why the temporary 3 stars rating on my side.

By Alex B

•

Aug 7, 2022

Considering that this is a refresh from an earlier course, some more attention could have been given to correctness of formulas used; there seems to be a real disconnect between Tensorflow programming assignment and other programming assignments - the Tensorflow functions were not well introduced

By Irina R

•

Apr 25, 2020

Andrew is an excellent teacher, but the programming assignments are weak. Everything is already written for the learner, and the only things one needs to do is to fill few lines of code here and there. To fully understand the material, the learner should write the code by himself/herself.

By Vishnu V S

•

May 6, 2020

I wish the course material on Tensorflow was updated to Tensorflow 2, but it is also nice to know what happens under the hood. I also wish there was some programming assignments in which we could tune some hyperparameters and visualise the difference between selecting diferent values.

By Jacob J

•

Dec 13, 2022

While reviewing the mathematics is important, not having any formal lectures discussing the lines of code became frustrating at times. A brief overview relating the mathematics to how it should be formatting written would be beneficial (especially when introducing Tensorflow).

By akshaya r

•

Jan 12, 2020

Good explanation of hyperparameters and optimization in DNN. As a beginner to tensor flow, I felt it hard to debug the tensor flow assignment. It would have been easier if the assignment included validation of each function before building the complete model.

By Salim S I

•

Aug 12, 2018

Would have liked programming assignment in python to understand the various initializations and optimizations. Although tensorflow introduction was good, It felt like being left stranded without a python assignment to cement the things learnt in the class.

By Brian W

•

Oct 17, 2019

The lectures are good and informative. However, the programming assignments are hard to learn from - an unhelpful combination of too easy and too obscure, so that it's hard to believe I'm developing skills that will help me program such things myself.

By Kevin J

•

Aug 1, 2020

Ich hätte mir gewünscht, dass Hyperparameter Tuning tiefer behandelt worden wäre.

Anstelle eines randomisierten Ausprobierens hätte ich mir mehr Erfahrungswerte gewünscht, wie man situationsabhängig Netze konstruiert und Parameter wählen sollte.

By Andrew W

•

Nov 2, 2019

The material is very well and intuitively explained. I am disappointed with the assignment. It seems to be based on older versions of Tensorflow, and seems a bit outdated. This becomes very clear if one tries to run the assignment locally.

By Patrick P

•

Sep 21, 2017

The course notes don't lend themselves for use as reference materials. The programming exercises are spoon-fed. The material is more up-to-date than Andrew Ng's Machine Learning course, but that set a higher standard for online education.

By John D G

•

May 23, 2018

the lectures in this course seemed very packed and rushed, squeezing in a lot of content that felt skipped over instead of delving into the math a bit. The jupyter notebooks also have alot of errata that haven't been updated in a while

By Brieuc D

•

Jan 31, 2024

This course does not go as deep as the previous one in the specialization and the transition to TF lacks some explanation (got stuck for a while during programming assignment because TF seems to lay out labels in rows vs cols in numpy)

By Maggie Z

•

Jan 7, 2022

I find the course material not very well organized especially in week 1, as there are lots of random tactics taught which don't seem to fall into a common theme. For example, weight initialization seems better belong to week 2.

By Vahid N

•

Jul 2, 2019

The exercise although long was only related to the last section. There are some mistakes already reported by the students but no action yet. This is a good course do not ruin the reputation by some minor unaddressed issues.

By sean j

•

Dec 23, 2019

It's a good lecture for background but the programming assignment is outdated. Tensorflow 1 is very uncomfortable and the assignment would have been a lot easier and intuitive if it was Tensorflow 2, Keras or PyTorch.

By Deeplaxmi

•

Apr 1, 2020

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.