Please explain training regression

Hi

I'm using neural network matlab tool.

it's hard to understand training regression, what is it means ?

what is the best performance?

I attatched my graph. please reply ASAP.

Thank you.

Answer 1

[Parag]

Hi

In the context of neural networks within MATLAB, the training regression plot serves as a valuable tool for evaluating the correspondence between the network's outputs and the target values. For a comprehensive understanding, you may refer to the official documentation available at

https://www.mathworks.com/help/deeplearning/ug/analyze-neural-network-performance-after-training.html

In this context, a regression coefficient ( R = 1 ) signifies a perfect fit, indicating that the network's outputs precisely match the target values. This suggests exceptional model performance. A high ( R ) value reflects that the model's predictions are in close alignment with the target values. When ( R = 1 ), the model demonstrates optimal performance on the training data. It is advisable to validate the model using test data to ensure robust generalization across different datasets.