简体   繁体   中英

How do weights work in an Artificial Neural Network for Prediction?

Suppose i have 4 input data set. I am trying to implement an artificial neural network like the diagram below. 在此处输入图片说明

After training the neurons,i get 10 weights. How do i use these 10 weights to predict on test data?.

(n X 4) -> Test Data (A)
(10 X 1) -> Trained Weights (w)
(n X 4) (4 X 1) -> Predicted Output (How are the weights used here?)

Aw = y Where A is my test data and w is my weights, y is the predicted output.

I think you misunderstood how neural networks work. This is a very good tutorial explaining this from the beginning: CodeProject

In short: By training the neural network you change its structure to fit your test data , by prediction you use the modified structure to calculate the output the same way as you calculated during the training, but you don't modify it now.

The technical post webpages of this site follow the CC BY-SA 4.0 protocol. If you need to reprint, please indicate the site URL or the original address.Any question please contact:yoyou2525@163.com.

 
粤ICP备18138465号  © 2020-2024 STACKOOM.COM