このコースについて
273,980

100%オンライン

自分のスケジュールですぐに学習を始めてください。

柔軟性のある期限

スケジュールに従って期限をリセットします。

中級レベル

Course 1 of the TensorFlow Specialization, Python coding, and high-school level math are required. ML/DL experience is helpful but not required.

約6時間で修了

推奨:4 weeks of study, 4-5 hours/week...

英語

字幕:英語

学習内容

  • Check

    Handle real-world image data

  • Check

    Plot loss and accuracy

  • Check

    Explore strategies to prevent overfitting, including augmentation and dropout

  • Check

    Learn transfer learning and how learned features can be extracted from models

習得するスキル

Inductive TransferAugmentationDropoutsMachine LearningTensorflow

100%オンライン

自分のスケジュールですぐに学習を始めてください。

柔軟性のある期限

スケジュールに従って期限をリセットします。

中級レベル

Course 1 of the TensorFlow Specialization, Python coding, and high-school level math are required. ML/DL experience is helpful but not required.

約6時間で修了

推奨:4 weeks of study, 4-5 hours/week...

英語

字幕:英語

シラバス - 本コースの学習内容

1
4時間で修了

Exploring a Larger Dataset

In the first course in this specialization, you had an introduction to TensorFlow, and how, with its high level APIs you could do basic image classification, an you learned a little bit about Convolutional Neural Networks (ConvNets). In this course you'll go deeper into using ConvNets will real-world data, and learn about techniques that you can use to improve your ConvNet performance, particularly when doing image classification! In Week 1, this week, you'll get started by looking at a much larger dataset than you've been using thus far: The Cats and Dogs dataset which had been a Kaggle Challenge in image classification!...
8件のビデオ (合計18分), 6 readings, 3 quizzes
8件のビデオ
A conversation with Andrew Ng1 分
Training with the cats vs. dogs dataset2 分
Working through the notebook4 分
Fixing through cropping49
Visualizing the effect of the convolutions1 分
Looking at accuracy and loss1 分
Week 1 Outro33
6件の学習用教材
Before you Begin: TensorFlow 2.0 and this Course10 分
The cats vs dogs dataset10 分
Looking at the notebook10 分
What you'll see next10 分
What have we seen so far?10 分
Getting ready for the exercise10 分
1の練習問題
Week 1 Quiz30 分
2
4時間で修了

Augmentation: A technique to avoid overfitting

You've heard the term overfitting a number of times to this point. Overfitting is simply the concept of being over specialized in training -- namely that your model is very good at classifying what it is trained for, but not so good at classifying things that it hasn't seen. In order to generalize your model more effectively, you will of course need a greater breadth of samples to train it on. That's not always possible, but a nice potential shortcut to this is Image Augmentation, where you tweak the training set to potentially increase the diversity of subjects it covers. You'll learn all about that this week!...
7件のビデオ (合計14分), 7 readings, 3 quizzes
7件のビデオ
Introducing augmentation2 分
Coding augmentation with ImageDataGenerator3 分
Demonstrating overfitting in cats vs. dogs1 分
Adding augmentation to cats vs. dogs1 分
Exploring augmentation with horses vs. humans1 分
Week 2 Outro37
7件の学習用教材
Image Augmentation10 分
Start Coding...10 分
Looking at the notebook10 分
The impact of augmentation on Cats vs. Dogs10 分
Try it for yourself!10 分
What have we seen so far?10 分
Getting ready for the exercise10 分
1の練習問題
Week 2 Quiz30 分
3
4時間で修了

Transfer Learning

Building models for yourself is great, and can be very powerful. But, as you've seen, you can be limited by the data you have on hand. Not everybody has access to massive datasets or the compute power that's needed to train them effectively. Transfer learning can help solve this -- where people with models trained on large datasets train them, so that you can either use them directly, or, you can use the features that they have learned and apply them to your scenario. This is Transfer learning, and you'll look into that this week!...
7件のビデオ (合計14分), 6 readings, 3 quizzes
7件のビデオ
Understanding transfer learning: the concepts2 分
Coding transfer learning from the inception mode1 分
Coding your own model with transferred features2 分
Exploring dropouts1 分
Exploring Transfer Learning with Inception1 分
Week 3 Outro36
6件の学習用教材
Start coding!10 分
Adding your DNN10 分
Using dropouts!10 分
Applying Transfer Learning to Cats v Dogs10 分
What have we seen so far?10 分
Getting ready for the exercise10 分
1の練習問題
Week 3 Quiz30 分
4
4時間で修了

Multiclass Classifications

You've come a long way, Congratulations! One more thing to do before we move off of ConvNets to the next module, and that's to go beyond binary classification. Each of the examples you've done so far involved classifying one thing or another -- horse or human, cat or dog. When moving beyond binary into Categorical classification there are some coding considerations you need to take into account. You'll look at them this week!...
6件のビデオ (合計12分), 6 readings, 3 quizzes
6件のビデオ
Moving from binary to multi-class classification44
Explore multi-class with Rock Paper Scissors dataset2 分
Train a classifier with Rock Paper Scissors1 分
Test the Rock Paper Scissors classifier2 分
Outro, A conversation with Andrew Ng1 分
6件の学習用教材
Introducing the Rock-Paper-Scissors dataset10 分
Check out the code!10 分
Try testing the classifier10 分
What have we seen so far?10 分
Getting ready for the exercise10 分
Outro10 分
1の練習問題
Week 4 Quiz30 分
4.8
18件のレビューChevron Right

人気のレビュー

by CMMay 1st 2019

A patient and coherent introduction. At the end, you have good working code you can use elsewhere. Remarkably, the primary lecturer, Laurence Moroney, responds fairly quickly to posts in the forum.

by RCMay 15th 2019

Excellent material superbly presented by world-class experts.\n\nSorry if this sounds sycophantic, but this series contains some of the best courses I've encountered in50+ years of learning.

講師

Avatar

Laurence Moroney

AI Advocate
Google Brain

deeplearning.aiについて

deeplearning.ai is Andrew Ng's new venture which amongst others, strives for providing comprehensive AI education beyond borders....

よくある質問

  • 修了証に登録すると、すべてのビデオ、テスト、およびプログラミング課題(該当する場合)にアクセスできます。ピアレビュー課題は、セッションが開始してからのみ、提出およびレビューできます。購入せずにコースを検討することを選択する場合、特定の課題にアクセスすることはできません。

  • 修了証を購入する際、コースのすべての教材(採点課題を含む)にアクセスできます。コースを完了すると、電子修了証が成果のページに追加されます。そこから修了証を印刷したり、LinkedInのプロフィールに追加したりできます。コースの内容の閲覧のみを希望する場合は、無料でコースを聴講できます。

さらに質問がある場合は、受講者向けヘルプセンターにアクセスしてください。