Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization に戻る

4.9

星

44,017件の評価

•

4,785件のレビュー

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....

Oct 31, 2017

Thank you Andrew!! I know start to use Tensorflow, however, this tool is not well for a research goal. Maybe, pytorch could be considered in the future!! And let us know how to use pytorch in Windows.

Jan 14, 2020

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.

フィルター：

by Dustin

•May 04, 2019

Nice illustration of the tricks including Batch-Norm, Optimization as well as Dropout, etc. Sometimes the lack of the theory is sort of unstatisfying, but considering the difficulty of a comprehensive intro for all of the above, it has been good enough for beginners to catch up with.

by A S M A M

•Jan 01, 2018

While the first course in the specialization is the perfect introduction to the realm of NN, this course is the place where I learned to implement a true Deep Network. It talks about various optimizations and parameters of the DL models. Bonus, it introduces the tensorflow framework.

by Ananth K

•Oct 24, 2017

Great course! Very well laid out approach to tuning a deep neural network. FInal introduction to Tensorflow was useful, but I think a lot of information was compressed into a single video. Suggest spreading this a little more. The Tensorflow programming assignment was pretty good.

by Alberto B H

•Oct 07, 2017

Genial curso en el que aprender como optimizar tu red modificando una serie de parámetros y usando diferentes algoritmos. Ademas genial introducción a Tensorflow con el que avanzar en el montaje de redes de manera rápida. Recomendado totalmente tras realizar el curso anterior a este.

by Anurag A

•Sep 10, 2017

This course is awesome. I never had this deep understanding of tuning hyperparameters, batch normalization and regularization before taking this course, though I went through several online material. The Tensorflow introduction and subsequent programming assignment is also excellent.

by Prabhat K P

•Jan 10, 2020

The best course ever. I am highly impressed with the way Andrew Sir teaches and the depth of the topic, that he explains. You will never be left with a question unanswered. I am grateful to you sir, it made my life. Looking forward to complete the rest of the specialization courses.

by Taras M

•Jul 26, 2018

It would be super cool if this course could be extended with pytorch just to compare with tensorflow. Usually courses are extended on udemy, for instance (not a marketing, just a comparison), even after all the materials are completed. It would be sand to have this course abandoned.

by M A

•Mar 21, 2020

As a 2-3yrs experienced deep learning developer should say that this specialization is awesome specifically this course, it's really practical every day to get a better result just tune the parameters as you've learned in the course and boom that's it you get a better model. Thanks

by Nektarios K

•Jan 08, 2018

Really loved this course! I believe it is really important for anyone who completed the first one to enroll on this one as well as it goes over many important topics that are critical in implementing Neural Networks. And finally, it goes over Tensorflow which was really fun to do!

by Emilio D P

•Sep 24, 2017

Fantastic course on Deep Learning. The concepts explained during the course are very useful, especially regularization (week 1) and optimization (week 2). The introduction to TensorFlow is great. This course has allowed me to read technical articles about DNN and understand them.

by Timothy G

•Jul 15, 2019

This course was very helpful learn so additional information on hyperparameters which help me out at work. Where I was tuning my own and was able to get 88%. After taking this course and implementing what I learned into auto tune my hyperparameters my accuracy went up to 91.33%.

by tgerlach

•May 30, 2018

This lectures + programming examples are very good for a kick start and to understand key concepts. I'm a mathematician, diving into deep learning. I really appreciate this course. The programming examples are valuable even if my python knowledge is on a beginners level. Thanks!

by Dipanjan G

•Feb 03, 2020

This again is an excellent insight on the hyper parameters and deep learning frameworks. The extreme prowess in the subject but at the same time a very lucid and relaxed style of teaching from Andrew helps quickly grasp these difficult concepts. Looking forward to much more!!!

by RAGHAV S

•May 25, 2018

This is such a crucial course to build upon the fundamentals of Neural Networks.

Especially the intuitions that Andrew has provided really add to the arsenal, I'm so glad I took this course.

Looking forward to the other courses in this specialisation.

Thank you Andrew/Coursera :)

by Erik E

•Oct 02, 2017

This is a great course!! In this course a lot of the previous concepts start to be refined and streamlined for efficient implementation. I feel like this course gave me a better handle on the concepts that have been building since my first Machine Learning course by Andrew Ng.

by Dishant G

•Sep 28, 2019

Very well explained each and every concept only I had struggle in gradient checking and every other video and quizzes are great. I hope after doing these courses I will definitely get a good career start after my graduation.

Andrew Ng Sir is Greatest teacher I have found yet.

by Miguel P d L

•Nov 26, 2017

Excellent course, even using intuitions Prof. Andrew Ng is able to communicate the very details of the different regularization approaches, as well how to do a good hyper-parameter search. Finally it introduces the TensorFlow framework with a very nice programming assignment.

by Yang Z

•Dec 15, 2019

This course gives learner a high level strategy in tuning hyperprameter. It teaches me not only the knowledge but also the intuition about the processes. It is also great to learn how to use Tensorflow framework in training models. Great job deeplearning.ai team and Andrew!!

by Kai-Peter M

•Oct 28, 2019

Great course!!! The best online course I have ever taken! I enjoyed almost every day I participated in that course, really an educational treasure! It is so comprehensive and detailed at the same time. Due to the good presentation of the topics it was really understandable.

by Mandar K

•Jul 22, 2019

Wonderful course and material. Andrew has a great way of explaining the topics in the simplest way. Although I had some issue with understanding the optimizers, I learned a great deal. However, This course needs a revamp using Tensorflow 2.0 for the tutorials :) Thank you

by Amit G

•Nov 06, 2017

there is a lot of materiel that is being discussed during the lectures, and all of it seems like it could be really relevant. I am missing a consolidated course deck - ie something like a deck of slides on all the important concepts that are being discussed, for reference.

by Kiet L

•Aug 27, 2017

Another awesome course by Andrew. I wish he was my professor in my grad school. I hope Coursera publishes all the notebooks + data on public github so I can redo all the exercise again. Too much info to digest in short amount of time. I can't wait for RNN and CNN courses.

by Syed M H J

•Jan 09, 2019

Easily the best course on diving under the hood of how a Neural Network actually works and how to tune to the satisfaction of our results.

A no brainer for sure. The best part the exercises. You MUST do the exercises to understand thoroughly how the systems actually work.

by WAN L

•Aug 01, 2018

I like this course, it details basic while popular technique we need to optimize neural networks. also the lectures on different optimization algorithms are very helpful for you to know details on how they run when we choose these algorithm in frameworks like tensorflow.

by Arun G

•Mar 22, 2020

Excellent course, giving a very good insight into how to approach building a deep neural network, the concepts of various parameters, tips on how to best achieve a good algorithm and a step by step walk through of the different algorithms, parameters and optimization.