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: 56,767
Рецензии: 6,515

О курсе

This course will teach you the "magic" of getting deep learning to work well. Rather than the deep learning process being a black box, you will understand what drives performance, and be able to more systematically get good results. You will also learn TensorFlow. After 3 weeks, you will: - Understand industry best-practices for building deep learning applications. - Be able to effectively use the common neural network "tricks", including initialization, L2 and dropout regularization, Batch normalization, gradient checking, - Be able to implement and apply a variety of optimization algorithms, such as mini-batch gradient descent, Momentum, RMSprop and Adam, and check for their convergence. - Understand new best-practices for the deep learning era of how to set up train/dev/test sets and analyze bias/variance - Be able to implement a neural network in TensorFlow. This is the second course of the Deep Learning Specialization....

Лучшие рецензии

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.

AM
8 окт. 2019 г.

I really enjoyed this course. Many details are given here that are crucial to gain experience and tips on things that looks easy at first sight but are important for a faster ML project implementation

Фильтр по:

6301–6325 из 6,437 отзывов о курсе Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization

автор: Ashkan R

23 дек. 2020 г.

I really like the course material, topics discussed, and neural networks in general. I also have a lot of respect and gratitude toward Andrew, but the way he organized quizzes and programming assignments are rather a monkey-see-monkey-do strategy. You rarely get challenged. Overall the course is worth taking, but I would not recommend this to more advanced practitioners.

автор: Siddharth D

24 апр. 2020 г.

I have written this before in the discussions. I feel, there should be assignments to implement everything from scratch. I feel, i can fill in the code, and understand ,most of the mathematical functions, and reasoning, but i am still not confident that i can "CODE" a new problem from scratch. I was really hoping this certification will give me practice to achieve this.

автор: Maysa M G d M

4 мар. 2018 г.

Some exercises were wrong , like Z3 em tensorflow model, you said z3=w*z2+b3, but it was A2 ,not Z2.

Several exercises did not check the result for each function, so when I arrived at the huge model function, it was hard to discover where I was wrong.

I think this third week could be two. I missed exercise with normalization, there were all with tensorflow.

автор: Dartois S

17 авг. 2017 г.

A bit less good than the previous course. It would have been good to have a chance to concretely implement Batch normalization. Then I think the tutorial on tensorflow needs more details and explanations of the what and why of the conventions. Anyway I was really happy to learn a bit about tensorflow, I hope I will use it more through the course.

автор: Amit C

20 нояб. 2019 г.

The fact that the lectures are not available to keep is problematic. Also, the programming assignments leave too little to do. Only few lines of code, that in most cases are simply copied from the problem description. It would make sense to broaden the programming tasks, and let the students really cope with many of the real-world challenges.

автор: Virgilio E

27 нояб. 2017 г.

The course explains great tips for optimizing and tuning NN, bu I miss some more practical examples where observing and compare results when applying the different techniques studied.

Also I miss a general schema of all optimization and tuning tips in order to know when and where apply each depending on conditions, etc.

автор: Till R

2 мар. 2019 г.

Exercises are too easy, and lectures are kind of boring. The Jupyter / iPython system does not run smoothly. I ended up downloading everything on my local computer, completing the assignment there, and then pasting the code into the coursera notebook. That makes the assignments take 50% longer than necessary.

автор: bob n

15 нояб. 2020 г.

Would have rated higher, lost 2 stars because uses Tensor version 1. Keeping courses current is very important to me. Rating 3 even that though I thoroughly enjoyed this course and learned what's under the covers in packages such as tensorflow. Not sure if there is an excuse for not updating the final lab.

автор: Tomer G

9 нояб. 2019 г.

The content is 5 stars.

However, technicalities of assignments not getting submitted and then needing to investigate in the discussion board what others did to be able to submit an assignment..

Assignments not getting submitted&graded is a criticial bug, that's why the temporary 3 stars rating on my side.

автор: Irina R

25 апр. 2020 г.

Andrew is an excellent teacher, but the programming assignments are weak. Everything is already written for the learner, and the only things one needs to do is to fill few lines of code here and there. To fully understand the material, the learner should write the code by himself/herself.

автор: Vishnu

6 мая 2020 г.

I wish the course material on Tensorflow was updated to Tensorflow 2, but it is also nice to know what happens under the hood. I also wish there was some programming assignments in which we could tune some hyperparameters and visualise the difference between selecting diferent values.

автор: Akshaya R

12 янв. 2020 г.

Good explanation of hyperparameters and optimization in DNN. As a beginner to tensor flow, I felt it hard to debug the tensor flow assignment. It would have been easier if the assignment included validation of each function before building the complete model.

автор: Salim S I

12 авг. 2018 г.

Would have liked programming assignment in python to understand the various initializations and optimizations. Although tensorflow introduction was good, It felt like being left stranded without a python assignment to cement the things learnt in the class.

автор: Brian W

17 окт. 2019 г.

The lectures are good and informative. However, the programming assignments are hard to learn from - an unhelpful combination of too easy and too obscure, so that it's hard to believe I'm developing skills that will help me program such things myself.

автор: Kevin J

1 авг. 2020 г.

Ich hätte mir gewünscht, dass Hyperparameter Tuning tiefer behandelt worden wäre.

Anstelle eines randomisierten Ausprobierens hätte ich mir mehr Erfahrungswerte gewünscht, wie man situationsabhängig Netze konstruiert und Parameter wählen sollte.

автор: Andrew W

2 нояб. 2019 г.

The material is very well and intuitively explained. I am disappointed with the assignment. It seems to be based on older versions of Tensorflow, and seems a bit outdated. This becomes very clear if one tries to run the assignment locally.

автор: Patrick P

21 сент. 2017 г.

The course notes don't lend themselves for use as reference materials. The programming exercises are spoon-fed. The material is more up-to-date than Andrew Ng's Machine Learning course, but that set a higher standard for online education.

автор: John D G

23 мая 2018 г.

the lectures in this course seemed very packed and rushed, squeezing in a lot of content that felt skipped over instead of delving into the math a bit. The jupyter notebooks also have alot of errata that haven't been updated in a while

автор: Daniel T

2 июля 2019 г.

The exercise although long was only related to the last section. There are some mistakes already reported by the students but no action yet. This is a good course do not ruin the reputation by some minor unaddressed issues.

автор: Sean J

23 дек. 2019 г.

It's a good lecture for background but the programming assignment is outdated. Tensorflow 1 is very uncomfortable and the assignment would have been a lot easier and intuitive if it was Tensorflow 2, Keras or PyTorch.

автор: Deeplaxmi

1 апр. 2020 г.

Thankyou for your great guidance sir. I am diploma student where we ain't taught much maths related to ML. I found difficult to understand mathematical equations. So i request you to upload a course on that too.

автор: Imad M

4 нояб. 2018 г.

Week 1 and week 2 needs more examples of python programming in the videos. The videos for week 3 were a lot more interesting. Without the python implementation examples in the videos, the course can be very dry.

автор: Nikolay B

5 дек. 2017 г.

Lessons are nicely explained

Assignments should be more challenging. Same as first course, this one basically make you cope-paste instructor notes and just change variable names to pass all assignments.

автор: Caleb M

4 июня 2019 г.

Enjoyed learning the concepts but it all seemed slow and tedious. It also seems like building up tensorflow throughout the weeks would be more useful then just piling it in the notebook at the end.

автор: Christopher D

1 авг. 2020 г.

It was a really good course, as I have come to expect when Andrew Ng is involved. The reason I only gave it three stars was for the sole fact that the version of Tensorflow is not up to the date.