This course is an introduction to sequence models and their applications, including an overview of sequence model architectures and how to handle inputs of variable length. • Predict future values of a time-series • Classify free form text • Address time-series and text problems with recurrent neural networks • Choose between RNNs/LSTMs and simpler models • Train and reuse word embeddings in text problems You will get hands-on practice building and optimizing your own text classification and sequence models on a variety of public datasets in the labs we’ll work on together. Prerequisites: Basic SQL, familiarity with Python and TensorFlow
이 강좌는 Advanced Machine Learning with TensorFlow on Google Cloud Platform 전문 분야의 일부입니다.
Sequence Models for Time Series and Natural Language Processing
제공자:
Course을(를) 수강하는 학습자
- Data Scientists
- Machine Learning Engineers
- Chief Technology Officers (CTOs)
- Data Engineers
- Research Assistants
강의 계획 - 이 강좌에서 배울 내용
주
1완료하는 데 4시간 필요
Working with Sequences
In this module, you’ll learn what a sequence is, see how you can prepare sequence data for modeling, and be introduced to some classical approaches to sequence modeling and practice applying them.
14개 동영상 (총 41분), 1 reading, 4 quizzes
14개의 동영상
Getting Started with Google Cloud Platform and Qwiklabs3m
Sequence data and models5m
From sequences to inputs2m
Modeling sequences with linear models2m
Lab intro: using linear models for sequences20
Lab solution: using linear models for sequences7m
Modeling sequences with DNNs2m
Lab intro: using DNNs for sequences19
Lab solution: using DNNs for sequences2m
Modeling sequences with CNNs3m
Lab intro: using CNNs for sequences19
Lab solution: using CNNs for sequences3m
The variable-length problem4m
1개의 읽기 자료
How to send course feedback10m
1개 연습문제
Working with Sequences
완료하는 데 15분 필요
Recurrent Neural Networks
In this module, we introduce recurrent neural nets, explain how they address the variable-length sequence problem, explain how our traditional optimization procedure applies to RNNs, and review the limits of what RNNs can and can’t represent.
4개 동영상 (총 15분), 1 quiz
4개의 동영상
How RNNs represent the past4m
The limits of what RNNs can represent5m
The vanishing gradient problem1m
1개 연습문제
Recurrent Neural Networks
완료하는 데 4시간 필요
Dealing with Longer Sequences
In this module we dive deeper into RNNs. We’ll talk about LSTMs, Deep RNNs, working with real world data, and more.
14개 동영상 (총 62분), 4 quizzes
14개의 동영상
LSTMs and GRUs6m
RNNs in TensorFlow2m
Lab Intro: Time series prediction: end-to-end (rnn)45
Lab Solution: Time series prediction: end-to-end (rnn)10m
Deep RNNs1m
Lab Intro: Time series prediction: end-to-end (rnn2)26
Lab Solution: Time series prediction: end-to-end (rnn2)6m
Improving our Loss Function2m
Demo: Time series prediction: end-to-end (rnnN)3m
Working with Real Data10m
Lab Intro: Time Series Prediction - Temperature from Weather Data1m
Lab Solution: Time Series Prediction - Temperature from Weather Data11m
Summary1m
1개 연습문제
Dealing with Longer Sequences
주
2완료하는 데 2시간 필요
Text Classification
In this module we look at different ways of working with text and how to create your own text classification models.
8개 동영상 (총 35분), 2 quizzes
8개의 동영상
Text Classification6m
Selecting a Model2m
Lab Intro: Text Classification47
Lab Solution: Text Classification11m
Python vs Native TensorFlow4m
Demo: Text Classification with Native TensorFlow7m
Summary1m
1개 연습문제
Text Classification
완료하는 데 1시간 필요
Reusable Embeddings
Labeled data for our classification models is expensive and precious. Here we will address how we can reuse pre-trained embeddings to make our models with TensorFlow Hub.
6개 동영상 (총 28분), 2 quizzes
6개의 동영상
Modern methods of making word embeddings8m
Introducing TensorFlow Hub1m
Lab Intro: Evaluating a pre-trained embedding from TensorFlow Hub24
Lab Solution: TensorFlow Hub9m
Using TensorFlow Hub within an estimator1m
1개 연습문제
Reusable Embeddings
완료하는 데 3시간 필요
Encoder-Decoder Models
In this module, we focus on a sequence-to-sequence model called the encoder-decoder network to solve tasks, such as Machine Translation, Text Summarization and Question Answering.
10개 동영상 (총 84분), 3 quizzes
10개의 동영상
Attention Networks4m
Training Encoder-Decoder Models with TensorFlow6m
Introducing Tensor2Tensor11m
Lab Intro: Cloud poetry: Training custom text models on Cloud AI Platform1m
Lab Solution: Cloud poetry: Training custom text models on Cloud AI Platform25m
AutoML Translation4m
Dialogflow6m
Lab Intro: Introducing Dialogflow54
Lab Solution: Dialogflow13m
1개 연습문제
Encoder-Decoder Models
완료하는 데 14분 필요
Summary
In this final module, we review what you have learned so far about sequence modeling for time-series and natural language data.
1개 동영상 (총 4분), 1 reading
1개의 동영상
Summary3m
1개의 읽기 자료
Additional Reading10m
4.5
26개의 리뷰50%
이 강좌를 수료한 후 새로운 경력 시작하기
67%
이 강좌를 통해 확실한 경력상 이점 얻기
Sequence Models for Time Series and Natural Language Processing의 최상위 리뷰
Great way to practically learn a lot of stuff. Sometimes, a lot of it starts to go over head. But, it is completely worth the learning curve! Definitely recommend it!
Excellent course for those who know RNN. Knowledge is refreshed and techniques are consolidated. More details about Google ecosystem is introduced.
Google 클라우드 정보
We help millions of organizations empower their employees, serve their customers, and build what’s next for their businesses with innovative technology created in—and for—the cloud. Our products are engineered for security, reliability, and scalability, running the full stack from infrastructure to applications to devices and hardware. Our teams are dedicated to helping customers apply our technologies to create success.
Advanced Machine Learning with TensorFlow on Google Cloud Platform 전문 분야 정보
This 5-course specialization focuses on advanced machine learning topics using Google Cloud Platform where you will get hands-on experience optimizing, deploying, and scaling production ML models of various types in hands-on labs. This specialization picks up where “Machine Learning on GCP” left off and teaches you how to build scalable, accurate, and production-ready models for structured data, image data, time-series, and natural language text. It ends with a course on building recommendation systems. Topics introduced in earlier courses are referenced in later courses, so it is recommended that you take the courses in exactly this order.
자주 묻는 질문
등록 전에 강좌를 미리 볼 수 있나요?
예. 등록하기 전에 첫 번째 비디오를 미리 보고 강의 계획을 검토할 수 있습니다. 미리 보기에 포함되지 않은 콘텐츠를 이용하려면 강좌를 구매해야 합니다.
강의 및 과제를 언제 이용할 수 있게 되나요?
세션 시작일 전에 강좌에 등록하면 해당 강좌의 모든 강의 비디오 및 읽기 자료에 접근할 수 있습니다. 수업이 시작되면 과제를 제출할 수 있습니다.
등록하면 무엇을 이용할 수 있나요?
등록 후 세션이 시작되면 읽기 자료 항목 및 강좌 토론 포럼을 포함하여 모든 비디오와 기타 리소스를 이용할 수 있습니다. 연습 평가를 보고 제출하며 필요한 성적 평가 과제를 완료하여 성적을 받고 강좌 수료증을 취득할 수 있습니다.
강좌 수료증을 언제 받게 되나요?
강좌를 성공적으로 수료하면 전자 강좌 수료증이 성취도 페이지에 추가됩니다. 해당 페이지에서 강좌 수료증을 인쇄하거나 LinkedIn 프로필에 수료증을 추가할 수 있습니다.
이 강좌를 청강할 수 없는 이유는 무엇인가요?
이 강좌는 현재 Coursera에서 수업료를 결제했거나 재정 지원(해당하는 경우)을 받은 학습자만 이용할 수 있는 강좌입니다.
환불 규정은 어떻게 되나요?
재정 지원을 받을 수 있나요?
궁금한 점이 더 있으신가요? 학습자 도움말 센터를 방문해 보세요.
Coursera는 세계 최고의 교육에 대한 보편적인 접근 기회를 제공하며,
최고의 대학 및 기관들과 제휴하여 온라인 강좌를 제공합니다.
© 2019 Coursera Inc. All rights reserved.
