Glossary
- Accountability
-
A principle of AI design to ensure that AI operates ethically, with human oversight and in alignment with legal standards, to manage the technology’s impact on society and individuals
- Accuracy
-
A metric, often used to evaluate classification models, that measures the proportion of correct predictions out of the total predictions made by a model
- Algorithm
-
A set of instructions that a model follows to analyze data and find patterns, enabling it to make predictions or classifications based on input features
- API (application programming interface)
-
A set of protocols that allows different software applications to communicate and interact with one another
- Attention
-
A mechanism in transformer models that assigns varying levels of importance to different words in a sequence, enhancing the model’s ability to understand contextual relationships
- Automated machine learning (AutoML)
-
An Azure Machine Learning feature that automates model selection and hyperparameter tuning by testing multiple algorithms to find the best model
- Azure AI Content Safety
-
A toolset for content moderation that enables automated detection and filtering of harmful or inappropriate content in online spaces
- Azure AI Custom Vision
-
A tool that enables users to create, train, and deploy custom image classification and object detection models that are tailored to specific needs and are accessible via software development kits (SDKs), an API, or a web portal
- Azure AI Document Intelligence ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access