Suggest to network architecture for two class classification problem by using MLP neural network

4 次查看（过去 30 天）
fred bnm
fred bnm 2016-11-4
回答： Greg Heath 2016-11-4
HI, please guide me for choose these parameters for binary classification by using MLP neural network .
number of samples : 300 (150 for class 1 and 150 for class 2)
train set = ?
validation set = ?
Test set = ?
number of input : 10 or 15 (depend on features)please explain The impact on the hidden layer for both numbers.
number of hidden layer : ؟
number of hidden neuron : ?
number of output neuron : ?
value for target matrix : (for example 1 and -1 , or 1 and 0)

请先登录，再回答此问题。

回答（1 个）

Greg Heath
Greg Heath 2016-11-4
Most of your questions can be answered from
1. The doc and help documentation examples
help patternnet
doc patternnet
2. My NEWSGROUP and ANSWERS posts using search words
greg patternnet
Hope this helps.
Thank you for formally accepting my answer
Greg

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