Course
Skills
Sequence Models for Time Series and Natural Language Processing on Google Cloud
In this course, we’ll learn how to make predictions on sequences of data.
What you'll learn
In this course, we’ll learn how to make predictions on sequences of data. We’ll cover common business use cases like- 1.time-series prediction and how to deal with more recent data points getting more relevance 2.translating entire sentences (aka sequences of words) into other languages 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.
Table of contents
Working with Sequences
42mins
- Course Introduction 2m
- Sequence data and models 5m
- From sequences to inputs 3m
- Modeling sequences with linear models 3m
- Getting started with GCP and Qwiklabs 4m
- Lab intro:using linear models for sequences 0m
- Lab: Time Series Prediction with a Linear Model 0m
- Lab solution:using linear models for sequences 7m
- Modeling sequences with DNNs 3m
- Lab intro:using DNNs for sequences 0m
- Lab: Time Series Prediction with a DNN Model 0m
- Lab solution:using DNNs for sequences 2m
- Modeling sequences with CNNs 4m
- Lab intro:using CNNs for sequences 0m
- Lab: Time Series Prediction with a CNN Model 0m
- Lab solution:using CNNs for sequences 4m
- The variable-length problem 4m
Recurrent Neural Networks
15mins
Dealing with Longer Sequences
62mins
- Introduction 3m
- LSTMs and GRUs 6m
- RNNs in TensorFlow 2m
- Lab Intro: Time series prediction:end-to-end (rnn) 1m
- Lab: Time Series Prediction with a RNN Model 0m
- Lab Solution: Time series prediction:end-to-end (rnn) 10m
- Deep RNNs 1m
- Lab Intro: Time series prediction:end-to-end (rnn2) 0m
- Lab: Time Series Prediction with a Two-Layer RNN Model 0m
- Lab Solution: Time series prediction:end-to-end (rnn2) 7m
- Improving our Loss Function 3m
- Demo: Time series prediction:end-to-end (rnnN) 4m
- Working with Real Data 11m
- Lab Intro: Time Series Prediction - Temperature from Weather Data 1m
- Lab: An RNN Model for Temperature Data 0m
- Lab Solution: Time Series Prediction-Temperature from Weather Data 12m
- Summary 1m
Text Classification
35mins
Reusable Embeddings
28mins
- Historical methods of making word embeddings 6m
- Modern methods of making word embeddings 9m
- Introducing TensorFlow Hub 2m
- Lab Intro: Evaluating a pre-trained embedding from TensorFlow Hub 0m
- Lab: Using pre-trained embeddings with TensorFlow Hub 0m
- Lab Solution: TensorFlow Hub 10m
- Using TensorFlow Hub within an estimator 1m
Encoder-Decoder Models
84mins
- Introducing Encoder-Decoder Networks 10m
- Attention Networks 5m
- Training Encoder-Decoder Models with TensorFlow 6m
- Introducing Tensor2Tensor 11m
- Lab Intro: Cloud poetry:Training custom text models on Cloud ML Engine 1m
- Lab: Text generation using tensor2tensor on Cloud AI Platform 0m
- Lab Solution: Cloud poetry:Training custom text models on Cloud ML Engine 25m
- AutoML Translation 5m
- Dialogflow 7m
- Lab Intro: Introducing Dialogflow 1m
- Lab: Getting Started with Dialogflow 0m
- Lab Solution: Dialogflow 13m
Summary
3mins
