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

4.9

40,139개의 평가

•

4,265개의 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.

Apr 06, 2018

Fantastic course! For the first time, I now have a better intuition for optimizing and tuning hyperparameters used for deep neural networks.I got motivated to learn more after completing this course.

필터링 기준:

교육 기관: Subham K

•Jan 05, 2019

It was so awesome .I got to know the minute details which would certainly help me in making a better deep learning model.

교육 기관: Arram B

•Jan 05, 2019

Thank you Andrew Ng Sir, you made every complex topic easily understandable with very efficient way.

Thanks for everything Sir!!!!

교육 기관: Sourav

•Jan 05, 2019

Learnt a great deal about tuning models. Concepts of regularization, batch norm and optimizers were very well explained.

교육 기관: Shayan A B

•Jan 05, 2019

Another well-taught course. Cant wait to complete more in the specialization.

교육 기관: pratik a

•Jan 04, 2019

A great course!!

교육 기관: Jorge B

•Jan 04, 2019

Very practical, clear and useful.

교육 기관: Sudheer P

•Jan 05, 2019

This course teaches the mechanics of deep neural networks and how to optimize the neural net. Prof goes at a reasonable pace so that the student understands the concepts.

교육 기관: GANHADHAR

•Jan 04, 2019

Great Learning . Thanks a Lot

교육 기관: Babu, C

•Jan 07, 2019

Excellent optimization techniques articulated very well

교육 기관: chanish a

•Jan 05, 2019

I never have enjoyed this much while studying.

교육 기관: Arsalan

•Jan 06, 2019

I believe a approach Sir takes while teaching the course makes it comparatively easy to learn the very difficult concept of deep learning.

교육 기관: Abdullah

•Jan 07, 2019

Very thorough explanation about the hyperparameters and optimization techniques.

교육 기관: Ajay S

•Jan 07, 2019

Really a Great course for the deep learning thanks coursera for prioviding me financial aid for the course and i am able to complete the course with in the time . Thanks a Lot .

교육 기관: Ruiliang L

•Jan 06, 2019

Help you get the best understanding of the deep learning

교육 기관: Qasid S

•Jan 06, 2019

Great Course!! This course should be part of every deep learning career path.

교육 기관: Dhananjaykuamr o

•Jan 08, 2019

great course

교육 기관: WALEED E

•Jan 08, 2019

The course is very useful for being acquainted with tuning hyper-parameters and modern optimization algorithms like momentum, RMSProp an Adam. It is also introducing how to prevent over-fitting efficiently from recent papers in addition to mini batching training data. Although it introduces TensorFlow in a brief way, the overall assessment needs some revision.

교육 기관: Lim K Z

•Jan 09, 2019

Really love your interviews with the prominent figures in the AI sphere - very inspiring and insightful. Particularly like the advice given by Yoshua Bengio. Keep it up!!!!

교육 기관: Aakash G

•Jan 08, 2019

Started with some basic tensors... so that's good. However I like how Andrew explains the effect of each hyper-parameter on the models output. Happy learning!

교육 기관: Syed M H J

•Jan 09, 2019

Easily the best course on diving under the hood of how a Neural Network actually works and how to tune to the satisfaction of our results.

A no brainer for sure. The best part the exercises. You MUST do the exercises to understand thoroughly how the systems actually work.

교육 기관: KimYunSu

•Jan 09, 2019

I liked it!

교육 기관: AlexZhao

•Jan 08, 2019

Awesome course

교육 기관: 江逸群

•Jan 09, 2019

Thanks so much for this course

교육 기관: Yannik L

•Jan 09, 2019

Excellent

교육 기관: dmitry p

•Jan 09, 2019

Good course, just jupyter notebook hangs