How to Show the Weight or Bias in a Neural Network?

32 次查看（过去 30 天）
Kai Hao Then
Kai Hao Then 2011-3-2
评论： Aswany 2023-12-6
How to show the weight/bias from every layer in my neural network? I am doing a feedforward neural network with 2 hidden layers. Furthermore, how to determine how many hidden layers should I use in a neural network? Currently I have 3 inputs and 1 output. When I want to increase the hidden layer to 3, an error occurred saying that I have not sufficient of input for 3 hidden layers.
  1 个评论
Shani
Shani 2013-11-19
I am trying to create a neural network, would you have any notes that I can use to aid me with that at all? please

请先登录，再进行评论。

请先登录，再回答此问题。

采纳的回答

Greg Heath
Greg Heath 2013-4-19
编辑：Greg Heath 2013-4-19
1. If the input/output transformation function is reasonably well behaved, 1 hidden layer is sufficient. The resulting net is a universal approximator.
2. However, if you need a ridiculously high number of hidden nodes, H, ( especially if the number of unknown weights Nw = (I+1)*H+(H+1)*O approaches or exceeds the number of training equations Ntrneq = Ntrn*O), you can reduce the total number of nodes by introducing a second hidden layer.
[ I Ntrn ] = size(trninput)
[ O Ntrn ] = size(trntarget)
3. Nevertheless, it is usually better to stick with 1 hidden layer and use a validation stopping subset (the default) and/or a regularized objective function (an option of mse: help mse) or a regularization training function (help trainbr)
4. Sometimes a ridiculously high number of weights is the result of using a ridiculously high number of inputs. So, it may be worthwhile to consider input subset selection before resorting to a second hidden layer.
For a single hidden layer
weights = getwb(net)
= [ Iw(:); b1(:); Lw(:); b2(:) ]
where
Iw = cell2net(net.IW)
b1 = cell2mat(net.b(1))
Lw = cell2mat(net.Lw)
b2 = cell2mat(net.b(2))
You can try an example if you want to see how getwb orders weights with 2 hidden layers.
Hope this helps.
Thank you for formally accepting my answer
Greg
  2 个评论
Sai Kumar Dwivedi
Sai Kumar Dwivedi 2015-3-18
The explanation you gave on your 2nd point
(I+1)*H+(H+1)*O < Ntrn*O
Is this some kind of heuristic or does it have mathematical background?
Aswany
Aswany 2023-12-6
what about a neural network with 7 number of hidden layers?

请先登录，再进行评论。

更多回答（2 个）

Manu R
Manu R 2011-3-6
编辑：John Kelly 2013-11-19
Neural net objects in MATLAB have fields you can access to determine layer weights and biases.
Suppose:
mynet = feedforwardnet % Just a toy example, without any training
weights = mynet.LW
biases = mynet.b
% weight and bias values:
%
% IW: {2x1 cell} containing 1 input weight matrix
% LW: {2x2 cell} containing 1 layer weight matrix
% b: {2x1 cell} containing 2 bias vectors
  2 个评论
Kai Hao Then
Kai Hao Then 2011-3-27
There should be numbers showing the weights and bias. The link you have shown me doesn't provide the way to show the weights and biases but the information only. Is there any other way?
Rahul
Rahul 2013-4-18
Display "weights" in this example and it will show numbers.

请先登录，再进行评论。

Rahul
Rahul 2013-4-18
or open "weights" in the Workspace.

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

Community Treasure Hunt

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

Start Hunting!

Translated by