Chevron Left
Вернуться к Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization

Отзывы учащихся о курсе Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization от партнера

Оценки: 57,364
Рецензии: 6,590

О курсе

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....

Лучшие рецензии

30 окт. 2017 г.

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.

13 янв. 2020 г.

After completion of this course I know which values to look at if my ML model is not performing up to the task. It is a detailed but not too complicated course to understand the parameters used by ML.

Фильтр по:

6426–6450 из 6,514 отзывов о курсе Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization

автор: Mohammad E

14 авг. 2020 г.

The course and the material are great. However, the codes in the labs have serious problems which should be solved.

автор: Lucas N A

6 мар. 2020 г.

Really helpful advises. I felt it was too focus on the implementation side but I liked the intuitions parts better.

автор: Rishabh G

28 апр. 2020 г.

Week 3 of the course does not have a practice problem for batch normalization. Wanted to implement it and learn.

автор: Ramachandran C

6 окт. 2019 г.

I found the video lectures useful to understand the concepts, but the programming exercises are over-simplified.

автор: Carlos V

20 июня 2020 г.

Would give more stars if the final assignment used Tensorflow@ and not an outdated version that is not in use.

автор: Pranshu D

6 мар. 2018 г.

More tensorflow related tutorials should have been there. The lectures turned a little boring and redundant.

автор: Adrian C

30 нояб. 2017 г.

So far, I think this course is weak on theory, seems rushed and should provide more in depth lecture notes.

автор: Vincent D W

26 окт. 2019 г.

Encounter Error in the final assignment, cannot complete the model, but the grader gives 100/100 anyway.

автор: Amit C

1 февр. 2019 г.

I wish the course mentors were more active on this course makes it a bit difficult to clear doubts

автор: Laura L

22 мар. 2018 г.

It does not make you think of the problems, just fill in the gaps. First course was better.

автор: Mostafa A E N

29 июля 2020 г.

Programming assignments are too easy and the answer is already given before the question.

автор: harsh

28 июня 2020 г.

Tensorflow is not at all user friendly, I'm sure better alternatives would've been there.

автор: Aviv D

25 апр. 2020 г.

I recommend adding a summary page at the end of each week to make sense the mathematics.

автор: Tanurima M

4 июля 2020 г.

The course is outstanding just the tensorflow library should be taught more in details.

автор: Pranjal S

15 мая 2020 г.

The technologies and the assignments should be updated to follow the latest standards

автор: Chaobin Y

3 нояб. 2017 г.

Maybe this course can merge with the 1st one. they both cover too little materials.

автор: AHMED A H P

12 сент. 2020 г.

WEEK-3 was a little bit messy, it would have been better if it was tensorflow 2

автор: joel a

25 апр. 2020 г.

taught concepts well, but the programming assignments felt like it was spoonfed

автор: Xin H

12 мая 2018 г.

Good: Contents on Tensor Flow

Bad: No real useful content compared the Course 1.

автор: Péter D

6 окт. 2017 г.

great lectures, simplistic programming assignements, ridiculously easy tests

автор: SAMBATH S

2 авг. 2020 г.

It would be better to use TF2 as there are lots of changes in the usages.

автор: 笛 王

18 янв. 2018 г.

Harder to understand. Overall quality is not as good as the first class.

автор: Kenneth Z

20 мар. 2018 г.

It is a bit abrupt to jump into tensorflow without explaining in depth.

автор: Rishab K

17 апр. 2020 г.

good course to learn, but more assignments should be introduce n week3

автор: Rajat K S

11 янв. 2020 г.

Most of the solutions to the assignment were written in instructions.