Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization(으)로 돌아가기

4.9

40,909개의 평가

•

4,352개의 리뷰

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....

Dec 06, 2019

I enjoyed it, it is really helpful, id like to have the oportunity to implement all these deeply in a real example.\n\nthe only thing i didn't have completely clear is the barch norm, it is so confuse

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

필터링 기준:

교육 기관: Keanu T

•Jun 26, 2019

I wish it went a little more in-depth with softmax classifiers but I can find that online so it's good.

교육 기관: José D

•Sep 07, 2019

This is Course2 of the Deep Learning Specialization. In Course1, we learned how to code the algorithm in Numpy. Most of Course2 show how to optimize and tune the algorithm and how to use and tune the hyper-parameters. Most assignments are well-designed and easy to perform as they focus more on the understanding than "finding how to code it". However, the last assignment introduces TensorFlow where we re-implement the algorithm using TensorFlow concepts. I have to say I expected TensorFlow to simplify things but it turns out I find the Math/Numpy implementation way easier to understand than TensorFlow. I'll have to dig deeper in TensorFlow concepts to understand it better. I would have liked more TensorFlow introduction. I hope the following courses will go into deeper details. Nevertheless, great course and very instructive.

교육 기관: Nguyễn H T

•Aug 20, 2019

I think this course is great. Because we learn about some definitions about hyperparameters, optimization which are frequently appears in papers or in the functions in some Deep Learning frameworks.

교육 기관: Hossein M

•Sep 09, 2019

too complicated, many lessens in couple of short videos.

poor video transcript

교육 기관: Yashika S

•Sep 10, 2019

tough one

교육 기관: Saurabh D

•Sep 12, 2019

Insights about how machine learning works in real life is quite ingeniuos.

교육 기관: Roy W

•Sep 13, 2019

Great course on hyperparameter tuning. Some of the code projects used the same variable names repeatedly in different contexts, which, to me, at least, is a bad practice to encourage in students. Also, in the Tensorflow project, some additional numerical calculations would have made it easier to catch issue earlier. But Andrew Ng was amazing, as always - clear and informative.

교육 기관: Marc D

•Sep 14, 2019

The course really takes the student by the hand through the exercises. The disadvantage is that it is not really necessary to understand what you are doing. Just follow the guidance. But on the whole really satisfactory

교육 기관: Gopal M

•Sep 14, 2019

TensorFlow is a bit nebulous.I need more practice.

교육 기관: Yuvini D S

•Dec 10, 2019

You can get a better insight as to how to improve neural networks that go beyond the fundamentals. The quizzes and assignments helps you get a hands-on experience of the theoretical material covered in the course.

교육 기관: Noah M

•Dec 10, 2019

With the basic knowledge I earned in course 1, it was very helpful attenting this coruse on improving Deep NN and I took a lot of notes during the course, to which can refer in the future.

교육 기관: אוריאל ב

•Dec 05, 2019

Hi

I enjoy the course a lot!

for tensor flow - I am not sure if its me or the course - but I need much more training to start thinking the tensor flow way. maybe i will practice more on real work cases.

thanks !

Oriel

교육 기관: Huy T T

•Dec 04, 2019

Overall, it's pretty good. I did have a problem understanding some of the facts being communicated about gamma and beta in batch norm. Also, I think there is a problem with the last notebook. My cost did not go down as fast.

교육 기관: André M

•Oct 24, 2019

4* only because the TensorFlow lectures and assignment were too much in too little time. Also from what I see, TF has massively changed syntax to 2.0 so it felt a bit pointless to learn TF1 syntax (which is ***horrible***) at this point. To me it detracted a lot from the learning experience.

The remaining lectures and modules were excellent as usual though. I'd still recommend this highly, and Andrew's insights into what tends to work and why are brilliant as always.

교육 기관: Tianhao C

•Oct 05, 2019

I like this course a lot! 4 star due to the programming assignment. It is well designed, but hope the assignment could be more challenging instead of just giving us a taste of deep learning.

교육 기관: Deepak K G S

•Oct 06, 2019

Very good presentation material and deep intuitive explanation by Professor Andrew NG . Quizzes are structured in a way that it will test all the sections you have learned in that week.Programming assignments will provide an idea on how to approach each of the problems.In addition to taking this course,I would also recommend you to try and code using the basic code structure presented in the lecture and assignments to build upon and see what works and what does not in the problems.Only then,you can see the benefit of what is taught in this lecture.

교육 기관: Sergey

•Oct 06, 2019

I wish prof. Ng provided more intuitions into underlying math particularly why gradient optimization techniques help. But like it anyways, very useful!

교육 기관: Ashraf A

•Oct 26, 2019

Very good course and a good introduction to the tensorflow

교육 기관: Christopher S

•Oct 25, 2019

Good intro to the available tools. Very guided course. For concepts to really stick, own projects or courses needed.

교육 기관: Cristhian A B

•Aug 28, 2019

It's a hard course but the materials are great and their explanations

교육 기관: Manpreet S B

•Oct 03, 2018

good course, easy to understand and very nicely explained concepts about the neural networks

교육 기관: alfredo g

•May 29, 2019

too math, i hope futher parts contain more implementation than calculus

교육 기관: Emmanuel T

•Oct 03, 2019

Compared to previous module, this one was more of a cookbook and I expected more mathematics in terms of why each optimization work.

Overall, it was still a very interesting hands on approach, finishing with TensorFlow is a bit more difficult to apprehend as all the previous exercices were done in a very different way (Numpy).

교육 기관: John H

•Aug 24, 2017

Well explained..sometimes jumps a bit. I felt lost a couple of times. But I got through it and I'd say this is deifnitely one of the top courses out there.

If they included some optional videos on how this could relate to having a career in this area that'd be very helpful (i.e. what level we need to be able to code at).

교육 기관: Manoj A

•Apr 18, 2018

There was no exercise on hyper-parameter tuning so the course seemed incomplete. I think week 3 should be split into 2 weeks with first week focusing on hyper-parameter tuning and second on TensorFlow.