In AI terminology, what does inference mean?

Inference, in AI, refers to the process where a pre-trained machine learning model is used to make predictions or decisions on new, previously unseen data. This is distinct from the training phase, where the model learns patterns from labeled data. For example, after training a model to recognize cats, inference is when that model is given a new image and predicts whether it contains a cat. Developing new AI algorithms is part of research and development, not inference. Combining models is ensemble learning. Gathering and preparing training data is data preprocessing.