Concerns about "Edit Shallow Neural Network Properties"

1 次查看（过去 30 天）
Khoi Ly
Khoi Ly 2019-6-4
Hi everyone,
This is my first attempt with neural network on Matlab and there is one thing I don't fully understand.
Under "Weight and Bias Values," I read the following statement:
Each input weight net.IW{i,j} has as many columns as the size of the jth input (net.inputs{j}.size) multiplied by the number of its delay values (length(net.inputWeights{i,j}.delays)).
Since I simply want to create a simple feedforward neural network (I know that I can use feedforwardnet function but I would like to try a custom one), I won't need any delays in the weights. According to the above statement and my matlab code, the net.IW{i,j} = [ ].
How would I initialize non-empty weights for my network?
Thanks

请先登录，再回答此问题。

回答（0 个）

类别

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

标签

产品


版本

R2018b

Community Treasure Hunt

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

Start Hunting!

Translated by