Model

How it is used

The central word of the field. You train, evaluate, deploy, serve and retrain a model; models can be small or large, open or closed, and they have versions. Informally people also say 'the model thinks…' or 'the model got it wrong'.

Example sentences

1. The new model is twice as fast but slightly less accurate on long documents.

2. Which model version is running in production right now?

Common collocations

• train a model
• deploy a model
• model version
• model performance
• pretrained model

Related terms

• trainTo teach a model by showing it many examples and repeatedly adjusting its parameters so that its outputs get closer to the correct answers.
• parameterA named input that a function or method accepts, listed in its definition. The actual value you pass in when you call it is called the argument.
• inferenceThe stage in which a trained model is used to produce outputs for new inputs, for example answering a user's question or classifying a new photo.
• deployTo put a new version of software onto servers or devices so that it starts running there, for example in a test environment or for real users.

This word in other fields

The same English word can have a different meaning in another field:

• model · Data Science & Analytics
• model · Artificial Intelligence & Machine Learning
• model · Architecture

More terms: Machine Learning and Data Processing

• artificial intelligence
• machine learning
• dataset
• training data
• label
• supervised learning
• neural network
• deep learning
• loss function
• overfitting
• test set
• accuracy