How to create a transfer function with variable parameter?

1 次查看（过去 30 天）
Alexandra
Alexandra 2016-2-25
评论： Greg Heath 2016-3-4
Hello, I would like to create a custom neural network with custom neurons that will have transfer functions of a type: y(x)=exp(-x/l), where l is a parameter that will be different for each neuron and I have to have ability to initialize it for each neuron separately.
This is an attempt to model a particular constitutive equation. Creating a custom network structure is not a problem (thanks to Greg Heath) !
Thank you in advance!

请先登录，再回答此问题。

回答（1 个）

Greg Heath
Greg Heath 2016-2-28
This doesn't sound right. The default FEEDFORWARDNET configuration with TANSIG, LOGSIG, or RADBAS hidden nodes is a Universal Approximator. Exponentials don't satisfy the UA criteria.
Maybe Googling "Universal Approximator" might help you understand. I've forgotten the details).
Hope this Helps.
Thank you for formally accepting my answer
Greg
  2 个评论
Alexandra
Alexandra 2016-2-29
Dear Greg! Thank you for the comment! Yes, you are right - in the classic approximation theorem transfer function should be non-constant, bounded and monotone increasing function (from Haykin) but what about for example non-localized rbf functions, for example cubic or linear? Actually i would say that the closest function to my example is Gaussian rbf. Theoretically RBFs are also feedforward networks...
WHat do you think? can it be possible to have and activation function with variable parameter in case of rbf nets?
Greg Heath
Greg Heath 2016-3-4
By a change of variable exp(-abs(x)/a) is equivalent to a Gaussian.
However, I don't know if it helps because I don't know why you want to do this.
Greg

请先登录，再进行评论。

类别

在 Help Center 和 File Exchange 中查找有关 Deep Learning Toolbox 的更多信息

标签

Community Treasure Hunt

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

Start Hunting!

Translated by