神经网络 - 从两个不同的 i/p 模式中查找 o/p
我有两种不同（未知关系）类型的输入模式，我需要设计一个神经网络，在其中我将根据这两种模式获得输出。但是，我不确定如何设计这样的网络。
我是 NN 的新手，但我正在尝试尽可能多地阅读。据我所知，在我的问题中，有两个 6*1 阶的输入矩阵和一个 6*1 阶的 o/p 矩阵。那么我应该如何开始呢？使用反向传播和单个隐藏层可以吗？
例如->
Input 1 Input 2 Output 0.59 1 0.7 0.70 1 0.4 0.75 1 0.5 0.83 0 0.6 0.91 0 0.8 0.94 0 0.9
如何确定权重矩阵和传递函数的阶数？
请帮忙。任何与此相关的链接也可以。谢谢。
I have two distinct (unknown relationship) types of input patterns and I need to design a neural network where I would get an output based on both these patterns. However, I am unsure of how to design such a network.
I am a newbie in NN but I am trying to read as much as I can. In my problem as far as I can understand there are two input matrices of order say 6*1 and an o/p matrix of order 6*1. So how should I start with this? Is it ok to use backpropogation and a single hidden layer?
e.g.->
Input 1 Input 2 Output 0.59 1 0.7 0.70 1 0.4 0.75 1 0.5 0.83 0 0.6 0.91 0 0.8 0.94 0 0.9
How do I decide the order of the weight matrix and the transfer function?
Please help. Any link pertaining to this will also do. Thanks.
如果你对这篇内容有疑问，欢迎到本站社区发帖提问 参与讨论，获取更多帮助，或者扫码二维码加入 Web 技术交流群。
绑定邮箱获取回复消息
由于您还没有绑定你的真实邮箱，如果其他用户或者作者回复了您的评论，将不能在第一时间通知您！
发布评论
评论（1）
最简单的尝试是将 2 个输入向量连接起来。这样，您将拥有 1 个长度为 12 的输入向量，这将成为从 R^{12} 到 R^{6} 的“教科书”学习问题。
这样做的缺点是，您会丢失来自不同来源的每 6 个输入的信息，但根据您的描述，听起来您对这些来源了解不多。无论如何，如果您对这两个源有任何特殊知识，您可以对每个源使用一些预处理（例如减去平均值或除以标准差），以使它们更加相似，但大多数学习算法应该没有它也可以正常工作。
至于尝试哪种算法，我认为规范的顺序是：线性机（感知器），然后 SVM，然后多层网络（用反向传播训练）。原因是，您使用的机器越强大，拟合训练集的机会就越大，但拟合“真实”模式（过度拟合）的机会就越小。
The simplest thing to try is to concatenate the 2 input vectors. This way you'll have 1 input vector of length 12, and this becomes a "text-book" learning problem from R^{12} to R^{6}.
The downside of this, is that you lose the information about each 6 inputs coming from a different source, but by your description it doesn't sound like you know much about these sources. Anyways, if you have any special knowledge of the 2 sources, you can use some pre-processing (like subtracting the mean, or dividing by the standard deviation) on each of the sources, to make them more similar, but most learning algorithms should also work OK without it.
As for which algorithm to try, I think the cannonical order is: linear machines (perceptron), then SVM, then multi-layer-networks (trained with backprop). The reason is, the more powerful the machine you use, the better chances you have to fit the train set, but less chances to fit the "true" pattern (overfitting).