Model Machine Learning
noun
Definition 1: An abstract mathematical construct, often formalized as a parameterized function or family of functions fθ:X→Y, that maps inputs to outputs [Machine Learning Glossary].
Example in context: “This is accomplished by using algorithms that adjust parameters such as weights and biases in a model that maps inputs to outputs through multiple layers of artificial neurons.” [Prašnikar et al. 2024]
Definition 2: A trained instance of such a construct, that is, a specific parameterization used to generate predictions on new data [Iskusstvennyi intellekt 2023].
Example in context: “The proposed model achieved an overall validation accuracy of 97.05% and testing accuracy of 76.25%.” [Kumar et al. 2024]
Related terms: trained model, model architecture, parameters, predictor, hypothesis function, classifier, neural model