I'm not sure if that answers your question but it looks for me that you ask about back propagation algorithm. That video is an easy to grasp overview https://www.youtube.com/watch?v=aircAruvnKk

Artificial neural networks (ANNs) are a type of machine learning model that is inspired by the structure and function of the human brain. ANNs consist of interconnected nodes or neurons that process information, and they can be trained on input/output data to learn complex patterns and relationships.The input data for an ANN can come from a variety of sources, depending on the specific application. In the case of an engine, the input data could include parameters such as temperature, pressure, fuel flow rate, and other sensor readings that provide information about the engine's operating conditions. This data can be used to predict the engine's performance, detect faults or anomalies, and optimize its operation.The output data from an ANN can also vary depending on the application. In the case of an engine, the output data might include predictions of engine performance, such as power output, fuel efficiency, and emissions. It could also include alerts for potential faults or anomalies that could indicate a problem with the engine.The specific input/output data used in an ANN will depend on the specific application and the goals of the model. However, in general, ANNs are flexible and can be adapted to a wide range of input/output data types and formats, making them a powerful tool for a variety of applications.