Once the model is built and evaluated, GCP provides a simple interface for using the model for predictions. In this case, the model is ready for the classification of documents in various categories based on keywords in the input data.
Using the model for predictions
by Anand Deshpande,
Manish Kumar,
Vikram Chaudhari
Hands-On Artificial Intelligence on Google Cloud Platform
- Title Page
- About Packt
- Copyright and Credits
- Contributors
- Preface
- Section 1: Basics of Google Cloud Platform
- Overview of AI and GCP
- Computing and Processing Using GCP Components
- Section 2: Artificial Intelligence with Google Cloud Platform
- Machine Learning Applications with XGBoost
- Using Cloud AutoML
- Overview of Cloud AutoML 
- Document classification using AutoML Natural Language
- Image classification using AutoML Vision APIs
- Performing speech-to-text conversion using the Speech-to-Text API
- Sentiment analysis using AutoML Natural Language APIs
- Summary
- Building a Big Data Cloud Machine Learning Engine
- Understanding ML
- Understanding how to use Cloud Machine Learning Engine
- Overview of the Keras framework 
- Training your model using the Keras framework
- Training your model using Google AI Platform
- Asynchronous batch prediction using Cloud Machine Learning Engine
- Real-time prediction using Cloud Machine Learning Engine
- Summary
- Smart Conversational Applications Using DialogFlow
- Section 3: TensorFlow on Google Cloud Platform
- Understanding Cloud TPUs
- Implementing TensorFlow Models Using Cloud ML Engine
- Building Prediction Applications
- Section 4: Building Applications and Upcoming Features
- Building an AI application
- A step-by-step approach to developing AI applications
- Overview of the use case – automated invoice processing (AIP)
- Designing AIP with AI platform tools on GCP
- Upcoming features
- Summary
- Other Books You May Enjoy
Using the model for predictions
-
No Comment
..................Content has been hidden....................
You can't read the all page of ebook, please click here login for view all page.