neural-network - 人工神经网络：选择初始神经元

Question

如何选择初始结构（神经元和它们之间的连接）？我的书只说明我们在训练网络之前一开始就给连接随机权重。

我认为我们会在训练期间像这样添加神经元：

1. 从一个完全空的网络开始
2. 我在训练期间生成的第一个值将不存在
3. 添加一个神经元来对应这个值，权重随机

Answer 1

What you are after is a self-organizing ANN. Usually, the way the connections are organized is man-made into a model that the developer thinks will have sufficient power to perform the computation neccessary. You can of course start with a random selection of nodes with random connections, but the evolution of such a network will probably take a lot longer time than a standard two or three layer network.

So, yes, you are right in that you would use a similar approach when doing a self-organizing network. Keep track of two sets of genetic algorithms, one for the structure and one for the weights (or combine the two in some devious way) and evolve as you please.

Answer 2

我不相信这个问题是关于自组织或 GA 进化的人工神经网络。听起来更像是关于最常见的 ANN：感知器（单层或多层），在这种情况下，网络的结构：层数和层大小，必须在开始时手动选择. 初始化权重的一个简单的初始经验法则是简单地选择 -1.0 和 1.0 之间的均匀随机值。