Creating custom Transfer Function with more learnable parameters

2 ビュー (過去 30 日間)
Alexia Irais
Alexia Irais 2022 年 11 月 11 日
編集済み: Sam Chak 2022 年 11 月 11 日
Hello!
I actually working with deep learning toolbox.
I'm making a comparative study of the transfer functions and some of them aren´t in the toolbox, this functions that I would like to try have more learnable parameters than the weights and biases in a "classical" function. For example:
xtansig= 2./(1+exp(x*(-2*n))+1;
What functions will I have to modify to create a new transfer function that, in addition to weights and biases, also finds the "x"?

回答 (1 件)

Sam Chak
Sam Chak 2022 年 11 月 11 日
編集済み: Sam Chak 2022 年 11 月 11 日
Edit: This article contains information about creating custom functions for NN.
I think there are some similarities between your function and the logistic function. Have you looked into the logsig function?
  1 件のコメント
Alexia Irais
Alexia Irais 2022 年 11 月 11 日
Hello Sam.
Thank you for your answer.
I have searched in all the transfer functions that matlab has, I don't understand how I could generate the new function so that it finds more parameters :(

サインインしてコメントする。

カテゴリ

Help Center および File ExchangeSequence and Numeric Feature Data Workflows についてさらに検索

製品


リリース

R2021b

Community Treasure Hunt

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

Start Hunting!

Translated by