About this Course
4.8
117개의 평가
17개의 리뷰

100% 온라인

지금 바로 시작해 나만의 일정에 따라 학습을 진행하세요.

탄력적인 마감일

일정에 따라 마감일을 재설정합니다.

중급 단계

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

완료하는 데 약 6시간 필요

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

영어

자막: 영어

배울 내용

  • 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

귀하가 습득할 기술

Inductive TransferAugmentationDropoutsMachine LearningTensorflow

100% 온라인

지금 바로 시작해 나만의 일정에 따라 학습을 진행하세요.

탄력적인 마감일

일정에 따라 마감일을 재설정합니다.

중급 단계

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

완료하는 데 약 6시간 필요

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

영어

자막: 영어

강의 계획 - 이 강좌에서 배울 내용

1
완료하는 데 4시간 필요

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 videos (Total 18 min), 6 readings, 3 quizzes
8개의 동영상
A conversation with Andrew Ng1m
Training with the cats vs. dogs dataset2m
Working through the notebook4m
Fixing through cropping49
Visualizing the effect of the convolutions1m
Looking at accuracy and loss1m
Week 1 Outro33
6개의 읽기 자료
Before you Begin: TensorFlow 2.0 and this Course10m
The cats vs dogs dataset10m
Looking at the notebook10m
What you'll see next10m
What have we seen so far?10m
Getting ready for the exercise10m
1개 연습문제
Week 1 Quiz30m
2
완료하는 데 4시간 필요

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 videos (Total 14 min), 7 readings, 3 quizzes
7개의 동영상
Introducing augmentation2m
Coding augmentation with ImageDataGenerator3m
Demonstrating overfitting in cats vs. dogs1m
Adding augmentation to cats vs. dogs1m
Exploring augmentation with horses vs. humans1m
Week 2 Outro37
7개의 읽기 자료
Image Augmentation10m
Start Coding...10m
Looking at the notebook10m
The impact of augmentation on Cats vs. Dogs10m
Try it for yourself!10m
What have we seen so far?10m
Getting ready for the exercise10m
1개 연습문제
Week 2 Quiz30m
3
완료하는 데 4시간 필요

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 videos (Total 14 min), 6 readings, 3 quizzes
7개의 동영상
Understanding transfer learning: the concepts2m
Coding transfer learning from the inception mode1m
Coding your own model with transferred features2m
Exploring dropouts1m
Exploring Transfer Learning with Inception1m
Week 3 Outro36
6개의 읽기 자료
Start coding!10m
Adding your DNN10m
Using dropouts!10m
Applying Transfer Learning to Cats v Dogs10m
What have we seen so far?10m
Getting ready for the exercise10m
1개 연습문제
Week 3 Quiz30m
4
완료하는 데 4시간 필요

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 videos (Total 12 min), 6 readings, 3 quizzes
6개의 동영상
Moving from binary to multi-class classification44
Explore multi-class with Rock Paper Scissors dataset2m
Train a classifier with Rock Paper Scissors1m
Test the Rock Paper Scissors classifier2m
Outro, A conversation with Andrew Ng1m
6개의 읽기 자료
Introducing the Rock-Paper-Scissors dataset10m
Check out the code!10m
Try testing the classifier10m
What have we seen so far?10m
Getting ready for the exercise10m
Outro10m
1개 연습문제
Week 4 Quiz30m
4.8
17개의 리뷰Chevron Right

최상위 리뷰

대학: 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.

대학: 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.

강사

Avatar

Laurence Moroney

AI Advocate
Google Brain

deeplearning.ai 정보

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

자주 묻는 질문

  • 강좌에 등록하면 바로 모든 비디오, 테스트 및 프로그래밍 과제(해당하는 경우)에 접근할 수 있습니다. 상호 첨삭 과제는 이 세션이 시작된 경우에만 제출하고 검토할 수 있습니다. 강좌를 구매하지 않고 살펴보기만 하면 특정 과제에 접근하지 못할 수 있습니다.

  • 수료증을 구매하면 성적 평가 과제를 포함한 모든 강좌 자료에 접근할 수 있습니다. 강좌를 완료하면 전자 수료증이 성취도 페이지에 추가되며, 해당 페이지에서 수료증을 인쇄하거나 LinkedIn 프로필에 수료증을 추가할 수 있습니다. 강좌 콘텐츠만 읽고 살펴보려면 해당 강좌를 무료로 청강할 수 있습니다.

궁금한 점이 더 있으신가요? 학습자 도움말 센터를 방문해 보세요.