Make a equation with weight and bias in ANN

9 次查看（过去 30 天）
sangmin yang
sangmin yang 2021-12-3
评论： sangmin yang 2021-12-8
Hello guys,
I'm currently making a ANN which is one hidden layer with 8 neurons, and one output layer with 1 neurons.
I wanna make the equation of prediction so that I can get the value when the new input value comes.
I've been using Artificial Neural Network tool box, and here is my guess.
Input value X
Layer 1 : y1 = Sigmoid(X*W1+b1)
Layer 2 : y2 = y1*W2+b2
However, When I doing like this, the output value is different with model.
How can I use the weights and bias in equation?
Thanks.

请先登录，再回答此问题。

回答（1 个）

Vineet Joshi
Vineet Joshi 2021-12-8
Hi
When you create a neural network, the weights and bias are usually randomly initialized (folllowing some distribution).
You can set weights and bias by using the following functions.
Separate biases and weight values from weight/bias vector
Set all network weight and bias values with single vector
Regards
  1 个评论
sangmin yang
sangmin yang 2021-12-8
oh, in that case, I already got it.
I just wanna make a equation using weights and bias which are one of the result of my NN network.
Thanks

请先登录，再进行评论。

类别

在 Help Center 和 File Exchange 中查找有关 Sequence and Numeric Feature Data Workflows 的更多信息

标签

产品


版本

R2021b

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by