From the course: Azure AI Engineer Associate (AI-102) Cert Prep: Implement Natural Language Processing Solutions
Join today to access over 24,900 courses taught by industry experts.
Train, deploy, and test
From the course: Azure AI Engineer Associate (AI-102) Cert Prep: Implement Natural Language Processing Solutions
Train, deploy, and test
- [Instructor] In this video, we'll use the language studio portal to train, deploy, and test our model. Creating your language understanding model is an iterative process. You train the model, test it interactively, or use a dataset, deploy the trained model, and then review the predictions that the model generates. Review of these predictions will help determine any additional changes you may need to make to get better performance from the model. The iterative process of model creation consists of four basic steps. You will iterate over these steps a number of times until your model is performing at acceptable levels of prediction. You'll need to revisit the model periodically once it's deployed to see how well your changes are performing. Training the model is the process of having it learn the intents and entities from the sample utterances you have provided. You are giving the model examples of utterances that you suspect users might make when interacting with your application…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.