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

4.9

40,838개의 평가

•

4,347개의 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....

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

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

필터링 기준:

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: alfredo g

•May 29, 2019

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

교육 기관: David D

•Oct 07, 2017

Last programming assignments had some errors in them that could've easily been corrected.

교육 기관: Leitner C S E S

•Aug 29, 2017

Excellent course. But -1 for using TensorFlow, a not-really-free framework, to introduce students to them.

교육 기관: David B

•Oct 05, 2017

W

e

e

k

3

e

x

e

r

c

i

c

e

c

o

u

l

d be improved

교육 기관: Dixing X

•Oct 16, 2017

programming assignments are too easy XD

교육 기관: Rohini J

•Apr 15, 2018

It was very helpful to learnt batch normalization, regularization and tensorflow. It definitely needs a lot of self study to learn about these topics for people who are not familiar. Some mathematical resources like links to pdfs and videos would be extra helpful.

교육 기관: Arsen K

•Sep 11, 2017

Great course. One star was taken off, as I would like to see more in-depth info on Batch Norm and a bit more discussion on how to compute gradients in case that is used. But generally that's a minor detail

교육 기관: Gianluca M

•Mar 14, 2018

Very short, but very interesting. Some more advanced topics are presented that students don't typically learn on coursera courses, such as improvements to gradient descent, batch normalization, and dropout.

교육 기관: Rahul K

•Jul 24, 2018

The best course in deep learning: Hyperparameter tuning, regularization and Optimization. The course is best among all the available courses over internet but it lacks availability of study materials (or reference to reading materials).

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: Elpidio E G V

•Apr 23, 2019

Great explanations on behind the scenes operations of optimization algorithms and general theory. Coming from a more practical background, it helped me grasp the concepts much better. I only wish the programming exercises were a little bit more challenging!

교육 기관: Nicolas M

•Mar 20, 2018

Good course but it would be interesting to add some other methodologies on learning rate ("Cyclical Learning Rates for Training Neural Networks", "Snapshot ensembles") and some explanations on categorical variables and embeddings matrix ("Entity Embeddings of Categorical Variables")

교육 기관: EURICO O D C D S C

•Jan 08, 2018

Having tensorflow is great. It's a must.

교육 기관: Stuart R

•Mar 11, 2018

Good course. Minor errors/typos in presented videos.

교육 기관: Francisco R

•Sep 20, 2017

Super interesting course where you'll have to come back a few more times because of the density of the theory. It's overwhelming the amount of hyperparameters you need to tune, but it also makes it challenging and less boring to set up neural networks and models

교육 기관: Alex N

•Sep 12, 2017

Good pace

Only drawback is that some of the safe checks are wrong in the programming assignments, even with the right seeds.

교육 기관: Shivank Y

•Jan 26, 2019

The course content is great but the ending lacks tensorflow implementation of regularisation, hyperparameter tuning, learning rate decay, etc. and aslo still not confident enough in those.

교육 기관: Marijan S

•Sep 09, 2018

I learned very useful info, but the last programming asignment with tensorflow was a pain in the a**

교육 기관: Suman D

•Jul 27, 2018

Awesome.

교육 기관: Mohit K

•Jun 22, 2018

Thanks for such amazing course. Add little bit more on Tensorflow fundamentals

교육 기관: IURII B

•Apr 03, 2018

Thank you

교육 기관: shudhatma

•Jun 17, 2018

A very good course

교육 기관: Eloi T P

•Sep 16, 2017

Great course giving insight on how to fine tune deep neural networks. I believe the contents need to be a bit polished but that's totally understandable given its early stage. The comments in the discussion group will for sure help to fix some typos and make this course even better.

교육 기관: 苑思域

•Aug 03, 2018

This one is actually a little bit better than the first one, maybe less content, maybe more understandable