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: 61,744

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


26 авг. 2021 г.

Amazing course which focus on the theoretical part of parameters tuning, but it needs more explanation of Tensorflow, as I felt a little lost in the last project. Except that, it is an amazing course.


4 апр. 2021 г.

Fantastic course and although it guides you through the course (and may feel less challenging to some) it provides all the building blocks for you to latter apply them to your own interesting project.

Фильтр по:

7001–7025 из 7,090 отзывов о курсе Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization

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: ognjen m

17 нояб. 2022 г.

last week is rushed and not greatly explained. Especially in the work assigment

автор: P A A H

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: Xieming L

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: Di W

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.

автор: Ganesan G

28 дек. 2017 г.

I am not getting to see the programming exercises that i have done :(

автор: Adam S

24 окт. 2022 г.

Some good stuff, but very slow, and the coding was pretty trivial.

автор: Jonghyun K

25 апр. 2020 г.

voice was too small compared to noises made by clothes and others.

автор: Aastha S

14 июля 2021 г.

More explanations required for functions used in tensorflow lab


13 мая 2018 г.

Good courses, the sound quality is very poor (high tone noise).

автор: Suhas M

20 янв. 2019 г.

Interface for evaluating is not great and assignments are easy

автор: Alexandra

4 сент. 2017 г.

The Tensorflow part should have started sooner in the course.

автор: Aloys N

1 июля 2019 г.

We could have more guidance on setting a tensorflow model


30 апр. 2018 г.

Lots of theory and not enough practical implementation.

автор: Stefan S

22 сент. 2020 г.

Content starts to feel old, but still interesting.

автор: Hasnaa T

10 февр. 2020 г.

the circulum was some hard and over detailed

автор: luca m

5 мая 2020 г.

I would have loved to have a session on TF2

автор: Kenneth C V

29 авг. 2019 г.

Course is a bit complex due to the subject