how do i generate samples of two input xor gate for neural networks

2014 8 24
2 个回答
回答已采纳
更新时间：2014 8 28
6 次查看（30 天）

 采纳的回答

Greg Heath
Greg Heath 2014-8-25

1 个投票

You mean 32 examples (a single sample is a set of multiple examples).
There are only 4 possible inputs. They are obvious.
Hope this helps.
Thank you for formally accepting my answer
Greg

4 个评论
显示 2更早的评论 隐藏 2更早的评论

Thirunavukkarasu
Thirunavukkarasu 2014-8-26
To simulate NN training of the XOR function, two input signals with 32 binary samples were used to estimate the magnitude of the signals traversing through the NN. The data were divided into three segments; with 24 samples for training (75%), four samples (15%) for validation leaving four samples (15%) for testing
Greg Heath
Greg Heath 2014-8-28
I don't understand.
1. There are only 4 possible input combinations.
2. round(0.15*32) = 5 => 22/5/5
Andy L
Andy L 2014-8-28
75% + 15% + 15%... I'll assume a typo
Andy L
Andy L 2014-8-28
Then it is not clear what you are asking - the question you posed is asking how to generate samples you now say you have done!

请先登录，再进行评论。

更多回答（1 个）

Andy L
Andy L 2014-8-28

1 个投票

To generate a "random" binary sequence check out this similar thread! http://www.mathworks.co.uk/matlabcentral/answers/114656-random-binary-sequence-generator. You need to do it twice (one per input) and specify the number number of samples in each sequence (32). I hope this is helpful.

类别

在 帮助中心 和 File Exchange 中查找有关 Deep Learning Toolbox 的更多信息

产品

标签

Community Treasure Hunt

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

Start Hunting!

Translated by