Machine learning
Models learn patterns from data and apply them to new inputs.
What is machine learning?
Machine learning is an area of artificial intelligence in which models learn patterns from data. These are used for predictions, classification or content generation, among other tasks. Learning methods vary. In supervised learning, examples contain known target values or classes; not every method needs such labels. Machine learning is not limited to neural networks either.
In a fictional service business, a model is to assign incoming messages to suitable concern categories. For the chosen supervised approach, the team needs appropriately labelled examples and checks results on suitable messages not used for training. Unclear cases go to people for handling. New wording or different request types can change suitability; good results on familiar training examples alone do not establish later usefulness.
Sources
Related terms
- Artificial intelligenceArtificial intelligence covers methods such as language processing and pattern recognition. Suitability is assessed against a specific task.
- Deep learningMachine learning with neural networks containing multiple processing layers.
- Neural networkA model of connected computational nodes with adjustable parameters.
- Generative AIGenerative AI produces content such as text, images or code. Quality is assessed against its intended use and available source information.
- Model cardA model card documents an AI model’s purpose, foundations, evaluation conditions and known limitations for a particular version.
- AI readinessAI readiness concerns the foundations of an AI project: objectives, usable data, skills, responsibilities and an operating workflow.
Articles on this topic
AI & Automation with ASES
AI assistants and automated workflows