Chevron Left
返回到 Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization

學生對 deeplearning.ai 提供的 Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization 的評價和反饋

4.9
57,960 個評分
6,669 條評論

課程概述

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....

熱門審閱

CV
2017年12月23日

Exceptional Course, the Hyper parameters explanations are excellent every tip and advice provided help me so much to build better models, I also really liked the introduction of Tensor Flow\n\nThanks.

XG
2017年10月30日

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.

篩選依據:

6426 - Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization 的 6450 個評論(共 6,591 個)

創建者 Łukasz

2019年5月2日

bugs

創建者 Aakarapu S P

2018年7月3日

good

創建者 Dheeraj M P

2018年2月23日

good

創建者 Mohamed S

2019年10月20日

e

創建者 Joshua P J

2018年6月7日

I've loved Andrew Ng's other courses, but this course was boring and not well-organized. The lectures were unfocused and they rambled a lot; they're nearly the opposite style of Prof. Ng's other material, which I found extremely well-organized. Most topics could be shortened 33-50% with no of clarity.

The course structure itself could use improvement:

The first part of Week 3 (Hyperparameter Tuning) belongs in Week 2.

The third part of Week 3 (Multi-Class Classification) should be its own week and its own assignment and could really be its own course. This is *THE* problem that almost every "applied" machine learning paper I've read is attempting to solve, whether by deep learning or some other class of algorithms. (Context and full disclosure: I'm a Ph.D. Geophysicist and my research is in seismology and volcanology.)

The introduction to TensorFlow needs to explain how objects and data structures work in TF. It really needs to explain the structure and syntax of the feed dictionary.

In the programming assignment for Week 3, there are three issues: (a) The correct use of feed_dict in 1.3 is completely new and cannot be guessed from the instructions or the TF website, and it's not clear why we use float32 for Y instead of int64; (b) In 1.4, "tf.one_hot(labels, depth, axis)" should be "tf.one_hot(labels, depth, axis=axis_number)". (c) In 2.1, the expected output for Y should have shape (6,?), not (10,?).

創建者 Francois T

2020年6月30日

As an old school (80s) software developer I feel uncomfortable about the lack of formal teaching on the structure and principles of TensorFlow. Sure, I can write the code and fly through the programming assignment, I "kind of" get it, but for a thorough engineer, that "kind of" creates a sense of unease. I wish Andrew Ng, being the incredible practical teacher he is with the theory of Machine Learning, would have spent a bit more time reviewing that particularly practical topic of TensorFlow more in depth, because 1h on it would bring much more value than say, understanding the inner working of batch norm, especially to an engineer ready to onboard a new project and start creating. For example, when should you use a placeholder vs a variable and why? Why is there a "name" parameter in the constructor of a variable, when should I make good use for the difference between the name at a tf level and its actual Python variable name? etc... Unlike Matlab or Numpy, TensorFlow looks to me like it could use a bit more theory before practice. Next class? :)

創建者 David M C

2019年7月22日

Nice explanation of Adam. Extremely minimal introduction to tensorflow; I felt unprepared to deal with all programming error messages I encountered when using TF. I would have liked to have had more exposure to softmax outputs as well; the multi-class case is new here. My biggest complaint is that there was quite a bit of time spent trying to explain batch normalization and no corresponding programming assignment. Also, in the past I felt I had my hand held a little too much in the programming exercises, whereas when tensorflow was introduced I felt I'd been thrown by that hand into the abyss; the expected output could not help me debug because it seemingly was designed to remind me over and over that tf.Session.run was needed to give value to tf variables. ya... I think you guys have some work to do on this course.

創建者 Todd J

2017年8月18日

Very mixed feelings about this course. The course title and nearly all (but 20 minutes) of the video content are on the topic of hyperparameter tuning, regularization and optimization of neural nets. This material is excellent. However, the programming assignment for Week 3 is about building a simple model in Tensorflow, with no coverage the rest of the material from the week. It is as if they included the wrong assignment, or just forgot to include the appropriate assignments to practice the actual content of the course. In addition, the Tensorflow intro in the videos and the Tensorflow assignment are not that great an introduction to the concepts behind Tensorflow. There are much better tutorials available on the web, such as from Tensorflow.org and codelabs.developers.google.com

創建者 Evan M

2020年7月31日

Please update course to use / teach tensorflow 2 syntax

Also this course... really holds your hands through the programming exercise. The code in each exercise is well organized into separate subfunctions, each of which has its own check, so its already simple enough to debug. But when this is couple with the fact that the instructions basically spell out what lines to put where (and give significant hints as to what functions to use in those lines...) the whole thing is completely trivialized. I think that I at least would have learned much better if I was forced to use man pages etc. to look up the usage of functions, for example.

創建者 Navaneethan S

2017年9月20日

This course was much less rigorous and theoretically-grounded than the first. There didn't seem to be much justification for any of the techniques presented, which was a stark contrast to the first course.

However, the topics are important and useful to know, so I'm glad they were covered. To me, the most useful sections were on softmax regression and deep learning frameworks, which I really enjoyed. The TensorFlow assignment was also interesting and (relative to the others) challenging.

I think there is a lot of scope for this course to be improved and I hope Dr Ng and team will do so in the near future.

創建者 Stefano M

2020年4月8日

(+) On the plus side: Andrew is always an excellent lecturer. Also, the python notebooks provided for the assignments are an extremely good guidance for structuring a deep neural network project.

(-) On the minus side: this course is rather disappointing compared to Andrew's well-known Machine Learning course on coursera. There is basically no challenge, as assignments (or, I would call them, "tutorials") are *very* guided: they can be completed even with a very shallow understanding of the content. Also, lectures are quite repetitive, and more like a practical cookbook than an actual course.

創建者 Peter G

2017年12月5日

Nice course, but again, main emphasis on the practical side and 'never mind, you don't need to know the details' approach. Having optional parts where theory about batch-normalization implementation and softmax derivative derivation could be shown - that would be very desirable. Another not so great thing is that final TensorFlow-related practice exercises are too 'quick' in a sense that 99% of the code is written for you and hints are given in such a way that you literally don't even have to use a half of your brain. That is also frustrating, when everything is already done for you.

創建者 Minglei X

2017年10月22日

Some process that was discussed in details in previous courses are mostly omitted in new context. While it is sometimes nice for saving time and focusing on new ideas, I feel like there are sometimes subtleties in them. Like I could not imagine how backward propagation should be implemented in batch norm. I'm not sure if it's because there are really some subtleties that you think it's too tedious and not necessary to introduce in the short video. If it is the case, I still hope you could provide more detailed information about them somewhere, just for curious people like me.

創建者 Ashvin L

2018年8月24日

The course builds up on the first course and provides some ideas on how to tune the networks to perform better. However, at the core, I find the number of parameters overwhelming and it appears that by changing the parameters we can get any answer we want. There is no "formal" and mathematical basis for changing the parameters. This is a bit disconcerting.

The assignments were trivial. More importantly, at least one assignment appeared to indicate that the results are entirely dependent on weights chosen (at random) on the first iteration. This should not be the case.

創建者 Vikash C

2019年1月28日

Content was good.

But the system that checks our submitted our code checks wrongly even when I wrote it correctly.

In week 2 assignment, when I submitted the code, it gave many functions as wrong coded.

I resubmitted the code after few changes, for instance a+= 2 changes to a = a+2 and string text like 'W' changes to "W". It worked fine and gave 100 points.

In short, what I observed is that the code checking system is taking a+=2 and a=a+2 as differently, also 'W' and "W" are considered different, but they are not in actual output.

創建者 William K

2018年10月1日

I thought the content was well-chosen and typically presented clearly. However, unlike the previous course in this specialization, the assignments had an egregious number of typos and missing information. I found these errors confusing and time-consuming.

From the staff's forum activity, it looks like they are no longer actively involved in this course. I hope that Coursera will hire someone—an intern would probably be plenty capable—to take this course and carefully fix as many of the errors in it as she or he can find.

創建者 Zbynek B

2020年6月9日

This is my third course by Prof. Ng, which I passed all with 100% score track. So far, I gave always 5 stars. This time, however, just three because of (1) weak explanation of the Dropout method (intuition) and (2) missing gradient for the extra gamma parameter (Batch Norm method). It isn't a big deal for the student to derive the gradient. However, I expected Andrew at least to mention that gradient for the back propagation step.

All in all I love the teaching style by Prof. Ng and I fully recommend them.

創建者 Kristof B

2021年4月8日

While i like the theoretical part of the course, the programming assignments need a lot of work. Foremost there is the issue of TensorFlow 1 being used. It isn't even the latest version of TensorFlow 1, but a very old one at that. Aside from that courses use too much hand holding, i find myself deliberately scrolling past information blocks so that i actually need to do some work. Otherwise it would just be copy pasting, or in other words, a waste of time.

創建者 Egnatious P

2020年4月19日

This was an interesting course in that it taught me a lot about hyperparameter tuning and how to improve my models in general. My main issue was that the optimization assignment couldn't open properly due to jupyter notebook issues and I didn't receive any support or direction on the issue. I just stumbled on the solution myself and this significantly messed up with my timelines. I wish there was more support for technical issues as well

創建者 Dimitrios G

2017年11月28日

The course continues on the same path the previous Deep Learning course has set but I found the use of TensorFlow somewhat limiting. It is a great tool that simplifies the training and running of NNs but it does not allow for easy debugging or for easy looking within the built-in functions to spot problems. I felt that we were treating many tf.functions as black boxes and I am not so fond of this. Otherwise the course was fairly useful.

創建者 Hamad

2019年9月12日

too easy.

One thing about Week 3 that I want to say, I had some confusions in the lectures but was hopeful that while going through the assignment I will clear out the concepts about tuning Hyper-parameters but instead, the assignment was ALL about tensorflow basics and nothing about tuning Hyper-parameters. I was really disappointed with that!

Other than that, course contents are great and worth the time and effort.

創建者 Jose F B

2021年3月7日

The course it's very good, but the reason I didn't put 3 stars is because it was difficult. I had the impression that the course was going too fast and I wasn't able to fully understand all the contents that the teacher gave. I think the assignments should be more similar to the first course, where you go step by step, understanding everything about the code. More explanations about tensorflow would be appreciated.

創建者 Younes A

2017年12月7日

Wouldn't recommend because of the very low quality of the assignments, but I don't regret taking them because the content is great. Seriously the quality of deeplearning.ai courses is the lowest I have ever seen! Glitches in videos, wrong assignments (both notebooks and MCQs), and no valuable discussions on the forums. Too bad Prof Ng couldn't get a competent team to curate his content for him.

創建者 Gadiel S

2018年9月21日

The course is good. It covers important ideas, and they are well explained in the videos. However, the formulation of the assignments is sloppy. There are mistakes and inconsistencies, in some cases necessary explanations are missing, and in some cases the instructions are misleading (I suspect the assignment has changed over time, but the instructions have not been consistently updated).