[英]Multiple artificial neural networks
I am trying to set up a Multiple Artificial Neural Network as you can see here on image (a): 我正在尝试建立一个多重人工神经网络,如您在图(a)上看到的:
I want that each of the networks work independently on its own domain. 我希望每个网络都可以在各自的域中独立工作。 The single networks must be built and trained for their specific task.
必须针对单个任务构建和培训单个网络。 The final decision will be make on the results of the individual networks, often called expert networks or agents.
最终决定权将取决于通常称为专家网络或代理商的各个网络的结果。
Because of privacy, I could not share my data. 由于隐私原因,我无法共享我的数据。
I try to set up this with Tensorflow in Python. 我尝试在Python中使用Tensorflow进行设置。 Do you have an idea of how I would do it if that is achievable?
您是否有想法在可行的情况下会如何做? At the moment I have not found any examples of this.
目前,我还没有找到任何例子。
The way to go about this is to just take the outputs of the two networks and concatenate the resulting output tensors (and reshape them if needed) and then pass them into the final network. 实现此目的的方法是仅获取两个网络的输出,并连接生成的输出张量(并在需要时对其进行整形),然后将其传递到最终网络中。 Take a look at here for the concatenation documentation and here for an example of taking the output from one network and feeding it into another.
请在此处查看串联文档,并在此处获取从一个网络获取输出并将其馈送到另一个网络的示例。 This should give you a place to start from.
这应该给您一个起点。
As for (a), it is simple, just train the networks before hand and load them when you are training the final network. 至于(a),这很简单,只需事先训练网络并在训练最终网络时加载它们。 Then do the concatenation on the outputs.
然后在输出上进行串联。
Hope this helps 希望这可以帮助
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.