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 deeplearning.ai

4.9
звезд
Оценки: 60,692
Рецензии: 7,031

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

JS

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.

NA

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:

451–475 из 6,977 отзывов о курсе Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization

автор: Ivan L

29 апр. 2019 г.

This course was a great introduction to more advanced topics of deep learning. I was primarily interested in the second week of this course, where different optimization techniques like momentum and optimization algorithms like ADAM were discussed.

автор: Raj

15 сент. 2021 г.

Had some issues with the last tensorflow assignment, since these are guided exercises wasn't able to debug my code properly (cost function was giving me a lower value, documentation didn't help me debug it either, will be looking into it further )

автор: Scott P

14 апр. 2018 г.

Great knowledge on how to optimize hyperparameters and example code is always appreciated. I appreciated the knowledge on effectively using sklearns hyperparameter search methods and knowledge on how to use tensorflow to create my own gpu methods.

автор: Filipe C d L D

4 июня 2020 г.

Excelente curso que explora o ajuste fino dos hiper-parâmetros, Regularização e Otimização dos modelos de Deep Learning. Recomendo fortemente este curso, pois o professor possui uma excelente didática e os exercícios são muito claros e objetivos.

автор: Jason M

28 мая 2020 г.

The course material was very good. The only issue I had was that the system seemed to go down once in a while, and I would have to exit and sign back into Coursera. Restarting the kernel didn't help. This would sometimes cause me to lose work.

автор: ashu a

20 апр. 2020 г.

considering the topics that are covered those are very good and detailed and as a beginner those are required to be known to every individual , especially professor andrew has put a lot of efforts in designing the course it seems , it's very nice

автор: Geoff L

29 авг. 2019 г.

Thanks to the instructor and the team for creating an excellent and rigorous online course. I particularly enjoyed learning the ADAM optimizer from the ground up. The quizzes and programming assignments are also challenging and fun. Thanks again!

автор: Gilberto B

21 янв. 2018 г.

This course teaches how to organise training in a structured and systematic way without doing things so complicated. Also very good introduction to tensorflow a library that any data scientist that is serious about deep learning should now about.

автор: Mohamed E

29 дек. 2017 г.

Very useful course which helped me to organize my thoughts about how to select the model hyperparameters, how to extended the network for multiple outputs using the softmax function. Additionally the Tensorflow lab was very helpful as jump start.

автор: Umang R

9 июня 2020 г.

After Completing this course I can now understand some of the secrets of Regularization, Batch Normalization, Learning Rate and many more thing related to Deep Learning.Assignments are very relatable to explore what you just learn in every week.

автор: Milton M

27 мая 2020 г.

Legendary Andrew Ng strikes again! Great chapter of this Deep Learning Specialisation! Good balance of theory and must-know concepts for improving neural networks! I especially appreciated the optimization part and the tensorflow coding exercise

автор: Dareer A M

20 мая 2020 г.

After completion of this course, I knew what I have to do to make my neural network to perform better and how to avoid over-fitting. And what range of values and techniques, I can use/check and how I will set my hyper-parameter more effectively.

автор: Kaveh H

18 мая 2018 г.

This is awesome.

Andre Ng gives great lectures, the practical exams are easy to follow and no installation of software and other annoying bumps on the road as everything you need is running smoothly using Jupyer notebooks on preinstalled servers!

автор: Ankit S

19 июня 2020 г.

This was the best course of this series as I have observed it was awesome to learn various normalization techniques and then implement them form the scratch and then the various optimizer. But in the last programming exercise the task was less.

автор: Lakshay

19 мая 2020 г.

A important aspect of machine learning that is left untaught and ignored that is hyperparameter and optimization.This course cover them all and also the best practices .Deeplearning.ai specialization is really the best course I have ever taken.

автор: Gopinath

22 дек. 2019 г.

Contents are structured in a way that it is so easy to pick up. Programming exercises are exactly in the balance that is not too hard or it isn't too easy. Learned a lot in this course especially. Thank you so much for this excellent course !!!

автор: Vasileios I

18 июня 2019 г.

A good summary of Hyperparameter tuning, Regularization and Optimization. One suggestion would be to extend this course for 1-2 weeks and emphasize more on the intuitions and mathematics behind the optimizers. But again, the videos are awesome.

автор: Fezan R

27 мая 2019 г.

Simple and straight forward explanation of most helpful tools. Examples are well designed. However I feel that introduction to TensorFlow is very brief, it should have been more elaborative. Anyhow overall a well designed and well paced course.

автор: HEF

27 мар. 2019 г.

This course taught me a lot of things that I cannot usually find in a school curriculum, yet the content are extremely useful in helping me to accelerate my algorithms. This course is super important in handling deep learning projects, I think.

автор: Srinath D

3 дек. 2018 г.

Another excellent course by Proffesor Ng. Lots of material to learn but neatly organized and extends the journey from the previous course. Lots of ML/DL terminology is clarified and their place and importance shown in this course. Very useful!!

автор: Michael D

21 мар. 2018 г.

Take this course if you want to know:

1). He Initialization

2). Adam Optimization

3). Batch Normalization

4). Softmax Activation (or regression)

5). Tensor-Flow for programming Deep-net.

It is an amazing course. It is well-structured and presented.

автор: Suvojeet D

25 авг. 2021 г.

Great course, learned a lot about hyperparamter tuning, different types of optimization methods, and regularization techniques. But, I felt more Tensorflow exercises are needed to get good grasp and use it smoothly to solve different problems.

автор: Diwakar P

6 июля 2020 г.

This is just an amazing Courese in Deep Learning, about neural network optimisation by chosing optimum hyperparameter. I would recommend every boy who i really interested in learning the deep thought of deep learning to go through this course.

автор: TAN S Y

3 мая 2020 г.

Understand well the fundamental and most of the hyper-parameters tuning mechanism and processes. The course has included some fundamental knowledge of using TensorFlow. It is well organized in the teaching processes and programming assignment.

автор: Teye B

27 мар. 2018 г.

Great Course. I especially like how the mathematics of Deep NNs are presented, taught and practiced, before the revelation of frameworks such as Tensorflow(in particular). This gives me a great understanding of what these frameworks are doing.