我收到了如下来自范恩的回复
Epochs 1. Current error: 0.2500066161. Bit fail 4.
Epochs 58. Current error: 0.0000930788. Bit fail 0.
位失败在这里意味着什么？
问问题
4153 次
3 回答
5
The bit fail limit is the maximum difference between the expected and actual output neuron value that is allowed.The default bit fail limit is 0.35. If the difference between the expected and actual output neuron value is more that the bit fail limit, this counts as 1 bit fail. In the sample output you gave, at 58 epochs all the output neurons gave actual outputs close enough to the expected outputs and hence the bit fail was 0 and training stopped. In other words all the training examples gave outputs that were close enough to the expected outputs. During the first epoch, 4 of the training samples gave outputs resulting in bit fails.
于 2014-03-20T10:52:29.230 回答
3
来自 FANN 的文档
失败位数；表示超过位失败限制的输出神经元的数量 http://leenissen.dk/fann/html/files/fann_train-h.html#fann_get_bit_fail
于 2012-10-17T09:35:13.953 回答
1
是的，我也发现这令人困惑，并认为这可能是“ruby-fann”中的一个错误。
FANN 手册指出它是失败的输出神经元的数量，但没有说它是提供的样本集的输出神经元数量的总和。因此，最坏的情况“位失败”是所有样本的所有输出神经元都失败（超出指定的位失败限制）。
于 2014-07-29T13:41:01.710 回答