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

4.9

40,004개의 평가

•

4,259개의 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 24, 2017

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.

Jun 03, 2018

Just as great as the previous course. I feel like I have a much better chance at figuring out what to do to improve the performance of a neural network and TensorFlow makes much more sense to me now.

필터링 기준:

교육 기관: Sijie J

•Jan 10, 2019

get a lot of insight about how to improve my own neural network.

교육 기관: Loay W

•Jan 10, 2019

I liked the Framework choice as TensorFlow and the project was nice!

교육 기관: Dunitt M

•Jan 11, 2019

Excelente curso, aunque me quedé con las ganas de implementar la normalización de lote en Numpy antes de usar TensorFlow.

교육 기관: aisibi

•Jan 12, 2019

good!

교육 기관: Hassan E

•Jan 13, 2019

Amazing

교육 기관: Aditya B

•Jan 12, 2019

The concepts has been explained in a fantastic way. But few suggestions:

-> After every lesson, I would love to have more pop quizes. This was the case with course 1, but I didnot get any pop quizes for this one.

-> In the quiz assignment, it would be nice to have an explanation or justification section, which will explain that why the option selected is a correct one and why the other options are incorrect. I know we can have the same discussion in the forums, but such an explanation ( one liner should be fine) can provide a good instant knowledge boost!

교육 기관: James C

•Feb 22, 2019

Very good course.

교육 기관: Rajnish C

•Feb 21, 2019

wanna know what going under hood , explore this one

교육 기관: Alyssa

•Feb 21, 2019

wonderful！！！！！

교육 기관: Luiz A N J

•Feb 10, 2019

Excellent course, the theoretical basis is given with amazing explanations by Andrew Ng. To best way to learn more about optimizations in Deep Learning.

교육 기관: Rohan G

•Feb 11, 2019

Gives quite an insight regarding all the hyper parameters and how to use them to get a good model.

교육 기관: 江小鱼

•Feb 12, 2019

This time , I finished Regularzation, I think this is a interesting experience, for you can implement your alg step by step, I get some magic(not black magic) alg, like RMS, momentum and Adam. At last, the most fascinating is to construct Tensorflow, just like a pipeline, step by step , and every step was made by only one line, from forward (without backward) to the model, Tensorflow is really black magic.

(I have to say Tensorflow is a bit difficult, forgive my poor English, thanks )

교육 기관: Shirish P

•Feb 12, 2019

Best

교육 기관: TanBui

•Feb 12, 2019

Perfect illustration as stated in the Title. You also get to learn and play with Tensorflow, which is one of the best programming frameworks to shorten the codes.

교육 기관: 陈浩然

•Feb 24, 2019

I learned a lot from this course.

교육 기관: Rohan K

•Feb 24, 2019

Phenomenal course on in deep learning

교육 기관: Yue

•Feb 23, 2019

Gracias, gran curso :)

교육 기관: Ahmet

•Feb 22, 2019

This is the first time, i have learned how the softmax classification, batch normalization, deep nn with tensorflow works, thank you Prof. Ng.

교육 기관: Jayant R

•Feb 24, 2019

I didn't knew much about different optimization algorithms and how they work. This course helped in understanding those concepts. Also leaened how to tune hyperparameters. Now, I am able to read tensorflow codes on net and also able to write basic code. Prof. Andrew Ng is the best. Concepts gets very clear on first time watching video.

교육 기관: Krystian P

•Feb 13, 2019

The homeworks (programming assignments) are a little bit an overkill.

교육 기관: Sam D

•Feb 12, 2019

Another wonderful course from Andrew Ng, and gives a good intro to tensor flow at the end. Looking forward to the next course!

교육 기관: Md. M H

•Feb 12, 2019

Great course and great tutorials on a deep learning framework.

교육 기관: Armand L

•Feb 25, 2019

excellent course

교육 기관: ABDUL A I

•Feb 24, 2019

Really learned a lot from this course. Hyperparameter tuning is something I now understand much better

교육 기관: Afiq S

•Feb 25, 2019

Though a little more complex for a Python beginner like me, I find it easy to follow :)