Sequence Models for Time Series and Natural Language Processing
- Offered byCoursera
- Public/Government Institute
Sequence Models for Time Series and Natural Language Processing at Coursera Overview
Duration | 15 hours |
Total fee | Free |
Mode of learning | Online |
Difficulty level | Advanced |
Official Website | Explore Free Course  |
Credential | Certificate |
Sequence Models for Time Series and Natural Language Processing at Coursera Highlights
- Shareable Certificate Earn a Certificate upon completion
- 100% online Start instantly and learn at your own schedule.
- Course 4 of 5 in the Advanced Machine Learning on Google Cloud Specialization
- Flexible deadlines Reset deadlines in accordance to your schedule.
- Advanced Level
- Approx. 15 hours to complete
- English Subtitles: English
Sequence Models for Time Series and Natural Language Processing at Coursera Course details
- 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
Sequence Models for Time Series and Natural Language Processing at Coursera Curriculum
Working with Sequences
Course Introduction
Getting Started with Google Cloud Platform and Qwiklabs
Sequence data and models
From sequences to inputs
Modeling sequences with linear models
Lab intro: using linear models for sequences
Lab solution: using linear models for sequences
Modeling sequences with DNNs
Lab intro: using DNNs for sequences
Lab solution: using DNNs for sequences
Modeling sequences with CNNs
Lab intro: using CNNs for sequences
Lab solution: using CNNs for sequences
The variable-length problem
How to send course feedback
Working with Sequences
Introducing Recurrent Neural Networks
How RNNs represent the past
The limits of what RNNs can represent
The vanishing gradient problem
Recurrent Neural Networks
Introduction
LSTMs and GRUs
RNNs in TensorFlow
Lab Intro: Time series prediction: end-to-end (rnn)
Lab Solution: Time series prediction: end-to-end (rnn)
Deep RNNs
Lab Intro: Time series prediction: end-to-end (rnn2)
Lab Solution: Time series prediction: end-to-end (rnn2)
Improving our Loss Function
Demo: Time series prediction: end-to-end (rnnN)
Working with Real Data
Lab Intro: Time Series Prediction - Temperature from Weather Data
Lab Solution: Time Series Prediction - Temperature from Weather Data
Summary
Dealing with Longer Sequences
Text Classification
Working with Text
Text Classification
Selecting a Model
Lab Intro: Text Classification
Lab Solution: Text Classification
Python vs Native TensorFlow
Demo: Text Classification with Native TensorFlow
Summary
Text Classification
Historical methods of making word embeddings
Modern methods of making word embeddings
Introducing TensorFlow Hub
Lab Intro: Evaluating a pre-trained embedding from TensorFlow Hub
Lab Solution: TensorFlow Hub
Using TensorFlow Hub within an estimator
Reusable Embeddings
Introducing Encoder-Decoder Networks
Attention Networks
Training Encoder-Decoder Models with TensorFlow
Introducing Tensor2Tensor
Lab Intro: Cloud poetry: Training custom text models on Cloud AI Platform
Lab Solution: Cloud poetry: Training custom text models on Cloud AI Platform
AutoML Translation
Dialogflow
Lab Intro: Introducing Dialogflow
Lab Solution: Dialogflow
Encoder-Decoder Models
Summary
Additional Reading
Other courses offered by Coursera
Student Forum
Anything you would want to ask experts?
Useful Links
Know more about Coursera
Know more about Programs
- Engineering
- Food Technology
- Instrumentation Technology
- BTech Chemical Engineering
- AI & ML Courses
- Aeronautical Engineering
- BTech Petroleum Engineering
- Petroleum Engineering
- VLSI Design
- MTech in Computer Science Engineering
- Metallurgical Engineering
- BTech Robotics Engineering
- BTech in Biotechnology Engineering
- Aerospace Engineering
- BTech Mechatronics Engineering