blocks|key|1462632|text|这是一个非常有趣的问题，但它不是那么容易回答。这取决于您试图解决的问题以及您尝试使用的神经网络。有几种神经网络类型。|type|unstyled|depth|inlineStyleRanges|entityRanges|data|1462633|一般来说，节点越多，精度越高，这一点不是很清楚。研究表明，大多数情况下只需要一个隐藏层。节点数应该是解决问题所需的最小节点数。如果你没有足够的解决方案--你将无法得到解决方案。|1462634|另一方面-如果你已经达到了很好的解决方案的节点数量-你可以添加越来越多的节点，并且你将看不到结果估计的任何进一步的进展。|1462635|这就是为什么有这么多类型的神经网络。他们试图解决不同类型的问题。所以你有神经网络来解决静态问题，解决与时间相关的问题等等。节点的数量并不像它们的设计那样重要。|1462636|entityMap^0|0|0|0|0^^$0|@$1|2|3|4|5|6|7|J|8|@]|9|@]|A|$]]|$1|B|3|C|5|6|7|K|8|@]|9|@]|A|$]]|$1|D|3|E|5|6|7|L|8|@]|9|@]|A|$]]|$1|F|3|G|5|6|7|M|8|@]|9|@]|A|$]]|$1|H|3|-4|5|6|7|N|8|@]|9|@]|A|$]]]|I|$]]

This is very interesting question but it's not so easy to answer. It depends on the problem you try to resolve and what neural network you try to use. There are several neural network types.

I general it's not so clear that more nodes equals more precision. Research show that you need mostly only one hidden layer. The numer of nodes should be the minimal numer of nodes that are required to resolve a problem. If you don't have enough of them - you will not reach solution. 

From the other hand - if you have reached the number of nodes that is good to resolve solution - you can add more and more of them and you will not see any further progress in result estimation.

That's why there are so many types of neural networks. They try to resolve different types of problems. So you have NN to resolve static problems, to resolve time related problems and so one. The number of nodes is not so important like the design of them.

blocks|key|1462696|text|当你有一个隐藏层时，你是在创建输入的组合特征。那么，是通过现有输入的更多特征更好地解决问题，还是通过组合现有特征的高阶特征来更好地解决问题呢？这是标准前馈网络的权衡。|type|unstyled|depth|inlineStyleRanges|entityRanges|data|1462697|你有一个理论上的保证，任何功能都可以用一个具有两个隐藏层和非线性激活的神经网络来表示。|1462698|此外，如果您不确定适当的拓扑结构，请考虑使用其他资源进行增强，而不是添加更多节点。|1462699|entityMap^0|0|0|0^^$0|@$1|2|3|4|5|6|7|H|8|@]|9|@]|A|$]]|$1|B|3|C|5|6|7|I|8|@]|9|@]|A|$]]|$1|D|3|E|5|6|7|J|8|@]|9|@]|A|$]]|$1|F|3|-4|5|6|7|K|8|@]|9|@]|A|$]]]|G|$]]

When you have a hidden layer is that you are creating a combined feature of the input. So, is the problem better tackled by more features of the existing input, or through higher-order features that come from combining existing features? This is the trade-off for a standard feed-forward network. 

You have a theoretical reassurance that any function can be represented by a neural network with two hidden layers and non-linear activation. 

Also, consider using additional resources for boosting, instead of adding more nodes, if you're not certain of the appropriate topology.

blocks|key|1677913|text|非常粗略的经验法则|type|unstyled|depth|inlineStyleRanges|entityRanges|data|1677914|通常，输入向量越大，每层的元素越多。|1677915|更多的层可以让您对更多的非线性系统进行建模。|1677916|如果您使用的网络具有传播延迟，则可以使用更多层对时间序列进行建模。注意在延迟中有时间抖动，否则它不会工作得很好。如果这对你来说只是胡言乱语，那就忽略它。|1677917|更多的层允许您插入重复出现的特征。这对于识别任务非常有用。你安的实现我不允许这样做。|1677918|HTH|1677919|entityMap^0|0|0|0|0|0|0^^$0|@$1|2|3|4|5|6|7|N|8|@]|9|@]|A|$]]|$1|B|3|C|5|6|7|O|8|@]|9|@]|A|$]]|$1|D|3|E|5|6|7|P|8|@]|9|@]|A|$]]|$1|F|3|G|5|6|7|Q|8|@]|9|@]|A|$]]|$1|H|3|I|5|6|7|R|8|@]|9|@]|A|$]]|$1|J|3|K|5|6|7|S|8|@]|9|@]|A|$]]|$1|L|3|-4|5|6|7|T|8|@]|9|@]|A|$]]]|M|$]]

Very rough rules of thumb

generally more elements per layer for bigger input vectors.

more layers may let you model more non-linear systems.

If the kind of network you are using has delays in propagation , more layers may allow modelling of time series . Take care to have time jitter in the delays or it wont work very well. If this is just gobbledegook to you, ignore it.

More layers lets you insert recurrent features. This can be very useful for discrimination tasks. You ANN implementation my not permit this.

HTH

blocks|key|1462812|text|每个隐藏层的单元数量说明了ANN描述任意复杂函数的潜力。一些(复杂的)函数可能需要许多隐藏节点，或者可能需要多个隐藏层。|type|unstyled|depth|inlineStyleRanges|entityRanges|data|1462813|当一个函数可以由一定数量的隐藏单元粗略地近似时，任何额外的节点都将提供更多的accuracy...but。只有当使用的训练样本足以证明这种相加是正确的时，这才是正确的-否则将发生“过度收敛”。过度收敛意味着你的神经网络已经失去了它的泛化能力，因为它过度强调了特定的样本。|1462814|一般来说，如果生成的网络可以提供良好的结果，最好使用尽可能少的隐藏单元。在大多数情况下，证明更多隐藏节点所需的额外训练模式不容易找到，并且准确性并不是NNs的强项。|1462815|entityMap^0|0|0|0^^$0|@$1|2|3|4|5|6|7|H|8|@]|9|@]|A|$]]|$1|B|3|C|5|6|7|I|8|@]|9|@]|A|$]]|$1|D|3|E|5|6|7|J|8|@]|9|@]|A|$]]|$1|F|3|-4|5|6|7|K|8|@]|9|@]|A|$]]]|G|$]]

The number of units per hidden layer accounts for the ANN's potential to describe an arbitrarily complex function. Some (complicated) functions may require many hidden nodes, or possibly more than one hidden layer.

When a function can be roughly approximated by a certain number of hidden units, any extra nodes will provide more accuracy...but this is only true if the training samples used are enough to justify this addition - otherwise what will happen is "overconvergence". Overconvergence means that your ANN has lost its generalization abilities because it has overemphasized on the particular samples.

In general it is best to use the less hidden units possible, if the resulting network can give good results. The additional training patterns required to justify more hidden nodes can not be found easily in most cases, and accuracy is not the NNs' strong point.

Generally speaking what do you get out of extending an artificial neural net by adding more nodes to a hidden layer or more hidden layers?

Does it allow for more precision in the mapping, or does it allow for more subtlety in the relationships it can identify, or something else?

Artificial Neural Network Question

人工神经网络

一般来说，通过向隐藏层或更多隐藏层添加更多节点来扩展人工神经网络，您会获得什么？它是否允许映射更精确，或者它是否允许在它可以识别的关系中更微妙，或者其他什么？

问人工神经网络问题
EN

社区

活动

资源

关于

腾讯云开发者

热门产品

热门推荐

更多推荐

问人工神经网络问题EN

社区

活动

资源

关于

腾讯云开发者

热门产品

热门推荐

更多推荐

问人工神经网络问题
EN