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

4.9

별

43,181개의 평가

•

4,645개의 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 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.

필터링 기준:

교육 기관: Maximilian B

•Sep 25, 2018

A lot of great concepts covered in the lectures but only few were explored in the assignments. The assignments seemed fairly simple to me.

교육 기관: Vanja T

•Sep 24, 2017

There were grading results that seemed wrong - I've submitted report on grading to explain details. Other than that, the course was great!

교육 기관: Aditya S

•Oct 05, 2019

Good course. However expected some more mathematical proofs for some of the ideas like bias correction and exponential weighted averages.

교육 기관: Prerna D

•Sep 07, 2019

Very good course. All the concepts explained very well. I just feel programming assignments were too easy, they could be a little tougher

교육 기관: Sidharth W

•Oct 19, 2018

Would have been 5 star but I found typos in the assignments and exercises -which have still not been corrected which is quite surprising

교육 기관: samarth

•Sep 12, 2017

Was a great course. Learnt conceptually and implemented Momentum,ADAM & rmsprop. Wish there were more exercises to explore TensorFlow .

교육 기관: Benjamin J

•Oct 30, 2017

I would have liked more programming exercises related to regularization and hyperparameter tuning, but TensorFlow was well introduced.

교육 기관: Ahmed N

•Mar 24, 2018

One of my best courses i have ever participated in, i gained a lot of knowledge and knew the underlying mathematics of every model.

교육 기관: Mathieu J

•Feb 24, 2018

Second step of the specialization,

a bit less rewarding than the fist course as more fine tuning and less overview of deep learning

교육 기관: Muiz V

•Oct 18, 2017

Programming assignments could have been more challenging. Otherwise, the course instructor is pretty awesome!! Thank you Andrew Ng.

교육 기관: Swann C

•Oct 06, 2017

Good material and definitely essential in order to gain a lot of time aiming at the right direction navigating all these parameters

교육 기관: aminedirhoussi

•Nov 22, 2019

Very good course. I would have liked a little longer introduction to the tensorflow architecture and less help on the assignements

교육 기관: Stanley C D

•Sep 05, 2018

A good introduction to gradient descent algorithms and hyperparameter tuning with a little TensorFlow thrown in for good measure!

교육 기관: Jorge

•Sep 23, 2017

Good course, Hyperparameter tuning, Regularization and Optimization are well explained, and the Tensor Flow lab is very useful too

교육 기관: Xin X

•Sep 19, 2017

Tips are very useful! Have some typos/errors in assignments, more coding work can help understanding. Thanks for sharing, Andrew!

교육 기관: JUI-CHIEH, W

•Aug 26, 2017

Many practical tricks such as tuning hyper parameters and the use of major optimization techniques such as batchnorm and dropout.

교육 기관: Victor-Hugo J

•Aug 04, 2018

Very interesting course. But a bit fast I would say. Sometimes I didn't feel the programming assignments were that challenging.

교육 기관: Uddhav D

•May 28, 2019

Again awesome explaining by Andrew, although I feel Batch Normalization should be a bit stressed upon and explained in detail.

교육 기관: Tarun S

•Sep 19, 2017

Well detailed course..

Tensorflow is very basic and it could have been improved if one can visualize graphs too in tensorboard

교육 기관: Steve A

•Nov 07, 2017

Great course!! The only improvements I'd suggest is more difficult assignments (less guided) and more written documentation.

교육 기관: Omar S

•Oct 29, 2017

Provides a good code skeleton to build a neural network, but would unlikely have one poised to do improvements on their own.

교육 기관: Om S P

•Jul 19, 2019

Some assignments, even though I get the same result as the output given, it get marked as wrong... Please try to rectify it

교육 기관: Victor P

•Oct 26, 2017

Very good course from the excellent Andrew Ng.

Some typos and some glitches in the video, hopefully it will improve in time.

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: Khalid A

•Sep 15, 2019

It is definitely very informative, but I wish the lectures would be more in depth in regards to the derivation and proofs.