if you want to interpret a model you likely want to explore something besides neural nets. That said you'll find a good tuto here: http://www.ling.uni-potsdam.de/~vasishth/sprache/docs/neuralnet.pdf
Moreover there is actualy many attemps to develop tools able to extract usefull information from black-boxes models such as ANN. Dalex is a good example: https://pbiecek.github.io/DALEX_docs/1-1-motivation.html
if you want to interpret a model you likely want to explore something besides neural nets. That said you'll find a good tuto here: http://www.ling.uni-potsdam.de/~vasishth/sprache/docs/neuralnet.pdf
Moreover there is actualy many attemps to develop tools able to extract usefull information from black-boxes models such as ANN. Dalex is a good example: https://pbiecek.github.io/DALEX_docs/1-1-motivation.html
In ANN, 70%of data is used for training, 15%testing and rest 15% for simulation. 1:1 correspondence graph appears as an output, which indicates the comparison between the measured and simulated variable
You can follow this link https://in.mathworks.com/matlabcentral/answers/61658-how-to-test-neural-network-with-real-world-data-after-training-it-how-to-interpret-output-of-ann