Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization に戻る

4.9

星

43,991件の評価

•

4,783件のレビュー

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....

Jan 14, 2020

After completion of this course I know which values to look at if my ML model is not performing up to the task. It is a detailed but not too complicated course to understand the parameters used by ML.

Oct 09, 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

フィルター：

by OMAL P B

•Feb 24, 2020

This is an wonderful course for people who want to learn about the ways to improve their models and make their best and more robust. Andrew Sir makes the math behind the scenes very easy to understand. The course is easy to follow as it gradually moves from the basics to more advanced topics, building gradually. Highly recommended.

by Tanveer M

•Aug 28, 2019

Professor Ng's very clearly put a lot of thought into breaking down deep learning into the most understandable way for students around the world and it shows through the quality of this course. I cannot recommend this course enough to anybody who is looking to do machine learning, or simply understand the process from a high level.

by Bernard O

•Oct 24, 2018

The tips and great guidelines one gets from this course are gems in their own right. Practitioners in particular will get to appreciate all the usable advice to improve their neural networks and at the same time get to understand the principles behind the scenes on what truly drives those optimizations. Highly recommended course.

by Sinkovics K

•Aug 15, 2018

The course material is detailed and comprehensive and presented in a very digestible way. I felt like the home works lack a few topics (e.g. learning rate decay implementation, which I would find to be a useful exercise), but they give you a good understanding of what is going on. All in all, I definitely recommend this course!

by jxtxzzw

•Mar 16, 2020

After learning the basic knowledge of the first course, this course deepened my understanding of deep learning, and explained how to optimize the model of deep learning from the perspectives of hyperparameter tuning, regularization and normalization, and finally provided the basic knowledge of the framework based on TensorFlow.

by Kazi M R

•Jun 06, 2018

From this course I have learnt several important hyper parameters, regularisation and optimization of deep neural network. Most importantly I got my first hand-on experience on Tensorflow framework by which creating deep net modes are quite easy if someone knows the elements of a deep net. I wish I will proceed for next course.

by Ian C

•Oct 01, 2017

Learning about TensorFlow is brilliant. It's very hard to get a good understanding of what goes on in TensorFlow without fully understanding the neural network coding setup. This course beautifully combines the two. There were some minor frustrations with the final TensorFlow programming exercise, but overall this is excellent.

by Jeroen M

•Jan 10, 2018

Great course, a few rough edges in the exercises and I also feel the exercise comments give away a bit too much (would be better if the student needed to figure out things by himself a little more). But these are minor details, I've learned a great deal in an amazingly short span of time, from one of the top minds in AI today!

by Jeff R

•Oct 02, 2017

I appreciate the large amount of time that has gone into preparing this course. I note that there are a large number of corrections in the errata forum that have not been reviewed by staff. In particular there are some obvious errors in the programming assignments that could easily be corrected with a small investment in time.

by Murat T

•Dec 24, 2018

Topics cut in to sections are well defined and so clear. Programming assignments definitely gives you hands on experience. Also, math is demystified that you track with high school math. If you used framework like Keras and you want to know why and when you need to use that function,parameter etc., you would love this course.

by Gilles D

•Sep 06, 2017

Eventually a clear and definitive explanation about Network initialization, regularization and optimization. Good insight share on hyper-parameters prioritization.

We learn the how and why and suddenly, it all becomes a little bit less mysterious. It is all clearly explained in a very accessible way.

Great value for my needs

by Xuefeng P

•Aug 29, 2017

This course really gives you a fundamental and practical ideas about the hyper-parameters of DNN, and the way of tuning them. The part I liked most is the last programming assignment ---- play with Tensorflow!!! The assignment walks you through Tensorflow structure and basics in a very organized fashion.

Highly recommended!

by Mihai L

•Jan 21, 2018

This course is also interesting. The art of tuning hyper parameters and other optimization techniques are very interesting and nicely explained.

The introduction to Tensorflow and assignment is also interesting.Overall the difficulty is not high but the concepts are really powerful and important ,most scaffollding is done

by Vlad M

•Sep 07, 2018

The course part is overall good.

The last assignment can be improved in two key ways:

The comment # Z3 = np.dot(W3,Z2) + b3 should be # Z3 = np.dot(W3,A2) + b3 - figured this out by myself without help from forums. :)

Also, the Adam optimization is not very apparent in the instructions - searched in the forums for issues.

by Brad M

•Aug 22, 2019

In my deep learning classes in academia, hyperparameter tuning was always "hand-waved" away - my questions were always deflected, or put off. This class answered every one of my questions, and made me more confident I'd be able to implement a DL system in industry, and be satisfied with the results. Very good course!

by Toby K

•Nov 01, 2019

I am working through the DL specialisation. Consistently good teaching style and the programming assignments are suitably pitched for getting the learner to pick up methods quickly e.g. Tensorflow syntax for self-application later. Good course and looking forward to the next in the series. Well done Andrew and team.

by Ankur T

•Nov 21, 2018

word is not sufficient signup and experience it. For a deep learning beginner who already have math background can easily understand concept behind it but for implementation you need to refer extra materials on internet and book too. Andrew Ng explain only concept and recipe but for practice you will struggle hard.

by afshin m

•Feb 05, 2018

This course is continuation and a requirement of the first course. Really like the learning style of how first course and the first 2 weeks of the second course taught neural networks by doing all the math and calculations manually and finally introduced Tensorflow with parallels of what was taught in the class.

by arulvenugopal

•Dec 17, 2017

This is another excellent course in this specialization. I enjoyed the programming assignments. The instructions, tips made Tensor flow coding section to be easy . However, few blocks consumed more than few hours, due to placeholders. logic and the TF documentation is overwhelming. I am proceeding to next course.

by Wei L

•Aug 26, 2017

This course is harder than the previous one. It teaches more details of tuning parameters and optimization in deep learning. In the end it also teaches tensorflow which is really helpful. It's like a programming course, nerally all the commands have been already provided, so it's not hard to get the code correct.

by 姜云鹏

•Nov 21, 2017

It is really good and teach me the basic understanding of DeepLearning back propagation and gradients optimization like Momentum, RMPS, Adam finally I learn how to use Tensorflow to train my model.

But there are some mistakes in the assignments and also in the grade so that it costs me a lot of time but useless.

by Vinodh R

•Nov 12, 2017

The course content was excellent. The only issue is that there were some glitches with the grading of the second week programming assignment, in that I could obtain the expected output, but with repeated submissions, there would be (different) sections which could not be graded due to unnamed technical issues.

by Renato L

•Jul 03, 2019

Excellent content and very well explained. Thanks for this amazing course.

The course cover the building blocks of a Neural network. Andrew (and his team) did a great job by organizing the content in an evolving way in which you have the chance to build the knowledge from each piece of a (deep) Neural Network.

by Bryan H

•May 28, 2018

Practical programming lessons, and well-paced enjoyable lectures.

Comments:

Move tutorials on TensorFlow to Course 3, which was the most obscure part of the course. TensorFlow isn't as intuitive as other numerical toolboxes, so spending more time on the foundations of TensorFlow might reduce the learning curve.

by Mojtaba H

•Feb 11, 2020

It covers very good tips and tricks to build and enhance deep learning model.

Andrew is the best teacher for ML and Deep Learning, he covers all theory and practice simultaneously.

In this course you can understand all mathematical intuitions and implementation of neural network from scratch by your own codes.