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: 59,731
Рецензии: 6,910

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

AS
18 апр. 2020 г.

Very good course to give you deep insight about how to enhance your algorithm and neural network and improve its accuracy. Also teaches you Tensorflow. Highly recommend especially after the 1st course

CV
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\n\nThanks.

Фильтр по:

251–275 из 6,854 отзывов о курсе Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization

автор: Murat T

23 дек. 2018 г.

Topics cut in to sections are well defined and so clear. Programming assignments definitely gives you hands on experience. Also, math is demystified that you track with high school math. If you used framework like Keras and you want to know why and when you need to use that function,parameter etc., you would love this course.

автор: Gilles D

5 сент. 2017 г.

Eventually a clear and definitive explanation about Network initialization, regularization and optimization. Good insight share on hyper-parameters prioritization.

We learn the how and why and suddenly, it all becomes a little bit less mysterious. It is all clearly explained in a very accessible way.

Great value for my needs

автор: Xuefeng P

29 авг. 2017 г.

This course really gives you a fundamental and practical ideas about the hyper-parameters of DNN, and the way of tuning them. The part I liked most is the last programming assignment ---- play with Tensorflow!!! The assignment walks you through Tensorflow structure and basics in a very organized fashion.

Highly recommended!

автор: Akash K

20 мар. 2021 г.

Really enjoyed the course as it covered a lot of regularization and optimization techniques in depth. Programming assignments are really easy as it needed to write only few lines of code but serves its purpose and enforces the learnings from lectures. Highly recommended to get the exposure before starting your own journey.

автор: Ali n

7 июля 2020 г.

Best course for learning Hyper parameter tuning, Regularization and Optimization topics further more the batch and other various optimization algos like momentum, Adam, Batch norm etc are much easier here. Please have a look on ground reality too, Take quiz before staring any course that this candidate is suitable or not

автор: Mihai L

21 янв. 2018 г.

This course is also interesting. The art of tuning hyper parameters and other optimization techniques are very interesting and nicely explained.

The introduction to Tensorflow and assignment is also interesting.Overall the difficulty is not high but the concepts are really powerful and important ,most scaffollding is done

автор: Ferry v A

22 мар. 2021 г.

This course provides a good overview of the optimalization techniques for neural networks. It refers to both the basics by providing an explanation of moving averages, and the advanced by providing references to academic literature. Finally, it provides the rules of thumb that a practitioner needs when iterating models.

автор: Vlad M

7 сент. 2018 г.

The course part is overall good.

The last assignment can be improved in two key ways:

The comment # Z3 = np.dot(W3,Z2) + b3 should be # Z3 = np.dot(W3,A2) + b3 - figured this out by myself without help from forums. :)

Also, the Adam optimization is not very apparent in the instructions - searched in the forums for issues.

автор: Adam F

1 нояб. 2021 г.

I completed the entire specialization and having nothing but good things to say. Highly recommend it! Lectures are engaging, and Andrew does a fantastic job explaining some very complex topics. Programming assignments are challenging in a good way. You’ll really feel like you’ve learned a lot by the time you’re done.

автор: Evandro R

22 окт. 2020 г.

Another wonderful course of this amazing specialization. I could say a lot of things, maybe even pages on how Professor Andrew it's the right person to teach you about Deep Learning but I'll shorten in this review and recommend the whole specialization for you! It's worthy and there's a lot of knowledge to be shared!

автор: Brad M

22 авг. 2019 г.

In my deep learning classes in academia, hyperparameter tuning was always "hand-waved" away - my questions were always deflected, or put off. This class answered every one of my questions, and made me more confident I'd be able to implement a DL system in industry, and be satisfied with the results. Very good course!

автор: Zeinab B

4 мая 2020 г.

This course will cover everything you need regarding your neural network performance. I always had questions on why and when you use Adam, SGD, etc. and after this course, I have a much better understanding of how to choose hyperparameters and optimization methods. I highly recommend this course to ML practitioners.

автор: Toby K

1 нояб. 2019 г.

I am working through the DL specialisation. Consistently good teaching style and the programming assignments are suitably pitched for getting the learner to pick up methods quickly e.g. Tensorflow syntax for self-application later. Good course and looking forward to the next in the series. Well done Andrew and team.

автор: Ankur T

21 нояб. 2018 г.

word is not sufficient signup and experience it. For a deep learning beginner who already have math background can easily understand concept behind it but for implementation you need to refer extra materials on internet and book too. Andrew Ng explain only concept and recipe but for practice you will struggle hard.

автор: Nhựt Đ M

26 июня 2021 г.

Great course! Help understand the mathematics and intuition behind hyperparameters and regularization methods. I feel the material is well-prepared. However, the last lab is quite confusing because I think we are not prepared enough about tensorflow fundamental throughout the course to really apply it in practice

автор: afshin m

5 февр. 2018 г.

This course is continuation and a requirement of the first course. Really like the learning style of how first course and the first 2 weeks of the second course taught neural networks by doing all the math and calculations manually and finally introduced Tensorflow with parallels of what was taught in the class.

автор: arulvenugopal

17 дек. 2017 г.

This is another excellent course in this specialization. I enjoyed the programming assignments. The instructions, tips made Tensor flow coding section to be easy . However, few blocks consumed more than few hours, due to placeholders. logic and the TF documentation is overwhelming. I am proceeding to next course.

автор: Wei L

26 авг. 2017 г.

This course is harder than the previous one. It teaches more details of tuning parameters and optimization in deep learning. In the end it also teaches tensorflow which is really helpful. It's like a programming course, nerally all the commands have been already provided, so it's not hard to get the code correct.

автор: Muhammad T

26 мая 2020 г.

As usual, Andrew is a great instructor. He taught very complex concepts in very simple language and used notations that were easy to understand and were consistent throughout the length of the course. WOULD DEFINITELY RECOMMEND. I am hoping to complete the specialization in less than a month. 2 down, 3 to go!!!

автор: 姜云鹏

20 нояб. 2017 г.

It is really good and teach me the basic understanding of DeepLearning back propagation and gradients optimization like Momentum, RMPS, Adam finally I learn how to use Tensorflow to train my model.

But there are some mistakes in the assignments and also in the grade so that it costs me a lot of time but useless.

автор: Mushfiqur R

3 мая 2020 г.

It was a good course on understanding various hyper-parameters, some regularization method, optimization of algorithms, various gradients and gradient checking, batch - mini batch, exponentially weighted average , some tuning algorithms and finally a small introduction to deep learning frameworks. RECOMMENDED!

автор: Vinodh R

12 нояб. 2017 г.

The course content was excellent. The only issue is that there were some glitches with the grading of the second week programming assignment, in that I could obtain the expected output, but with repeated submissions, there would be (different) sections which could not be graded due to unnamed technical issues.

автор: Shubham S

8 мая 2021 г.

Amazing course by Andrew sir really helps understanding the mechanism of optimizing a machine learning model , the practices he taught will help me in speeding a better model with better accuracy .

Thanks to Coursera and Andrew sir for sharing the knowledge and experience of various legends of machine learning

автор: Muhammad A k

6 апр. 2020 г.

5/5.Thank you sir for helping me in my career.I recommend everyone to go through this course if you really want to learn detail about hyper parameter tuning , optimizers and regularization used to make neural network better. It helps to open black box of Neural network and know in detail about how all works.

автор: Renato L

3 июля 2019 г.

Excellent content and very well explained. Thanks for this amazing course.

The course cover the building blocks of a Neural network. Andrew (and his team) did a great job by organizing the content in an evolving way in which you have the chance to build the knowledge from each piece of a (deep) Neural Network.