Model input refers to the data or parameter that is fed into a machine-learning model for training or inference.
In supervised learning, input data consists of labeled examples with corresponding targets, and the model learns to predict outcomes for new, unseen examples.
In unsupervised learning, the model discovers patterns or relationships in input data without the use of labeled examples.
Optimizing model input through techniques such as feature selection and data preprocessing can improve the performance and accuracy of a machine-learning model.
Scale your model risk management
Learn how technology can transform how you and your team manage model risk.
Share
