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: 60,986

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


23 дек. 2017 г.

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



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:

501–525 из 7,030 отзывов о курсе Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization

автор: CLAUDIO A

24 июля 2019 г.

pretty good course all in all !, I would say considering the difficulty of this topics, the instructor has done a great job in transmitting the relevant parts that one needs to remember and also in justifying why things are as they are.

автор: Alexandre R

29 дек. 2018 г.

Very well structured class as a follow-up to the first one. Heavy on information but this is a good thing. As someone who isn't pro at Python, the development part was much smoother since programming wise it is similar to the first one.

автор: Santiago I C

5 дек. 2018 г.

En línea con los anteriores. Muy teórico pero perfecto para entender los entresijos del funcionamiento de los algoritmos. Si acaso echo en falta algo más de tensorflow pero supongo que se verá en el resto de cursos de la especializacion

автор: Rahul Y

18 нояб. 2018 г.

I really like the practical aspects of the course where although there is a focus on teaching the fundamentals, there is also a good focus on teaching the latest frameworks to apply the knowledge of the learnt concepts more efficiently.

автор: stewart n

24 февр. 2018 г.

Excellent practical advice on running NNs. The lectures teach the subject matter in a lucid and intuitive way. The course ends with a TemperFlow exercise that shows how to implement NNs at a higher level than peviously shown with numpy.

автор: Alejandro M

12 нояб. 2017 г.

Great material. Short, precise videos.

It would be great if you propose projects to work on outside the course, in order to learn more about the topics. Just like ideas where we could apply what we have learned and a seed to build upon.

автор: Jagdeep S

29 окт. 2017 г.

Loved the programming assignments. After learning Tensor flow in this course, I learnt about Keras on my own. It made model building very easy, but without understanding the basics, going straight to Keras would make a person dangerous.

автор: Carlson O

1 окт. 2017 г.

Again, the course was great. Covering a large spectrum of deep neural net adaptations and configurations of its hyperparameters give me a better understanding and tips with how to best use this deep learning technology. Congratulations!

автор: George M

15 мая 2021 г.

Very good and interesting course!

Programming assignments were a bit easy, but it does not bother me as this is not an "introduction to programming" course. The point is to get the basic ideas of programming these kinds of applications.

автор: Hemanth R

19 авг. 2020 г.

Absolutely loved the course. have learnt the basic pillars of Neural Networks and DNN. Andrew has clearly explained the diagnosis of a problem and identify bias and variance. then Regularisation techniques, Optimisation algorithms etc.

автор: Gaetano S

5 мая 2020 г.

Thanks to this course I finally learned to optimize a neural network through the tuning of parameters and hyperparameters. And then I finally had my first experience with Tensorflow.

Absolutely recommended. Andrew never disappoints me.

автор: Thomas L

8 окт. 2019 г.

I can't emphasize how much I enjoyed this course. The course material is clear, structured and well laid out and each concept builds on the previous with repeated emphasis on key walk away points. Can't wait to start the next course :)

автор: Ali S

19 мар. 2019 г.

This is a great course like other ones in this specialization. I learned from this course why we need regularization, how to do them exactly, what are the rules-of-thumb for setting hyperparameters, and how to find them systematically.

автор: Parth D

20 февр. 2020 г.

After learning neural network and deep learning it is important to learn improving networks.This course gives idea to improve your network.Only knowing how to build a neural net is not okay you should also know to improve the network.

автор: Sriram G

24 июня 2018 г.

Had a lot of confusions on why and how to tune hyper parameters. Got a good amount of knowledge in Mini batch, batch normalization, momentum, Adam and RMS prop. Will surely be useful when I tune hyper parameters in my future projects.

автор: Scott G

17 февр. 2018 г.

Great course. It was a little short, but covered the necessary parts of hyperparameter tuning. I also liked how the last homework was done using TensorFlow and how the courses in the specialization build upon the preceding lectures.

автор: Zhan S

26 окт. 2017 г.

Teaches "what it is" and "how to do it". Clear steps, easy to follow. It would be great if you can also teach "why it is like this", or say, why is regularization valid, what is the theoretical justification behind regularization etc.

автор: Tarry S

6 окт. 2017 г.

Excellently taught by Andrew Ng. While the field of Deep Learning and AI continues to evolve rapidly, Andrew maintains calm and explains the core and relevant aspects needed to succeed in this course and hopefully also in your career.

автор: Prakhar P

22 июня 2021 г.

I learned a lot of techniques which I can apply in improving my deep learning projects. Very happy to have selected this specialization course. Andrew Ng's style of teaching and imparting a complex topic with examples is unmatchable.

автор: Derick N T

2 окт. 2020 г.

Very clear and concise explanations. The advice from the instructor's personal experience is particularly exciting. It provides guidance and assures you that you are on the right part. This course is great to help develop intuitions.

автор: Tommi J

14 июля 2020 г.

Another great course which is an essential companion to the first course so that you know different techniques for improving and troubleshooting your neural networks. The 3rd week exercise also contains a nice tutorial to TensorFlow!

автор: Sowmya A

19 сент. 2019 г.

As with the first course of this specialization, Professor takes one step at a time building/ explaining things. He explains even minor details, so it very easy to understand. Also the assignments are very useful to learn the topics.

автор: Hardik G

1 апр. 2021 г.

Very important course in the path of specializing in deep neural network. The working of optimization and Regularization algorithms help you understand the way to improve the deep neural network thorough tuning the hyper parameters.

автор: Shrikant A

5 янв. 2020 г.

It has been a very helpful course for me. I got a proper intuition behind the hyperparameter tuning because of this course. Professor Andrew Ng's pedagogy and coursework design is just perfect and i really enjoyed learning from him.

автор: Omar A

15 окт. 2019 г.

Very Important topic in ML projects. The course gives the intuition for parameters of neural networks and how to choose them. Although slow pace with only a rough idea about each parameter but It is highly recommended for beginners.