Voir la documentation de annScore
The annCode action generates SAS DATA step scoring code from a trained artificial neural network model. This allows for the deployment of the model outside of the CAS environment, enabling scoring of new data in traditional SAS environments. The generated code can be saved to a CAS table for further use.
La acción annCode genera código de puntuación del DATA step de SAS a partir de un modelo de red neuronal artificial entrenado previamente con la acción annTrain. Este código puede ser utilizado para puntuar nuevos datos en entornos SAS tradicionales, permitiendo la implementación del modelo fuera del entorno de CAS.
The `annTrain` action, part of the `neuralNet` action set, is used to train an artificial neural network (ANN) in SAS Viya. This process involves adjusting the network's weights based on a given dataset to minimize prediction errors. The action supports various architectures like Multi-Layer Perceptrons (MLP), Generalized Linear Models (GLIM), and direct connection models. It offers extensive customization options, including different activation functions, optimization algorithms (like LBFGS and SGD), and data standardization methods, making it a versatile tool for building predictive models.