输出层中神经元的数量 [英] number of neuron in output layer
问题描述
我是人工神经网络的新手，但请帮助我解决这个问题?
I am new to Artificial neural network but please help me with this question?
我正在尝试实现用于字符识别的人工神经网络(使用MLP和SNN)，我是否需要在输出层中使用与需要识别的字符数相同数量的神经元.例如，如果我希望我的网络能够识别大写字母，小写字母和数字，我是否需要在输出层中有26 + 26 + 10个神经元.
I am trying to implement an artificial neural network for character recognition (using MLP, and SNN), do I need to have same number of neurons in the output layer as the numbers of characters required to be identified. For example do I need to have 26+26+10 neurons in output layer if I want my network to be able to identify capital letters, small letters and digits.
如果我必须识别Unicode字符集中的所有字符，我将需要在输出层中有多少个神经元.
what if I had to identify all the characters in the Unicode character set, how many neurons in the output layer will i need.
是否有任何方法(动态阈值)来减少此数量或在输出层中动态添加神经元?
Are there any methods(dynamic threshold) to reduce this number or to dynamically add neurons in output layer?
如果可能，请提供研究文章的链接. 谢谢.
Please provide links to research articles if possible. Thanks.
推荐答案
不，您不需要outputlayer大小来匹配类的数量.
No, you don't need the outputlayer size to match the number of classes.
我认为您需要了解的是输出层的输出只是网络输入的表示.话虽如此，您可以拥有想要的 any 输出层.如果您希望使用一种可以反映类的编码，则减少层中节点数量的最简单方法就是使用二进制编码.
I think what you need to understand yet is that the output layer's output is simply a representation of the network's input. That being said, you can have any output layer you want. If you want an encoding that mirrors your classes, the easiest way to reduce the number of nodes in the layer would be to use binary encoding.
示例:您可以使用3个神经元，而不是对8个类使用8个节点(每个类1个节点):
0类是输出0-0-0
1类是输出0-0-1
...
第7类是输出1-1-1
Example: Instead of using 8 Nodes for 8 Classes (1 node per class), you can use 3 neurons:
Class 0 is the output 0-0-0
Class 1 is the output 0-0-1
...
Class 7 is the output 1-1-1
我想你明白了.当然，您不仅可以使用二进制，还可以使用您可以想到的(或Google)任何编码方法.
I think you get the idea. Of course you can use not only binary but literally any encoding method you can think of (or google).
这篇关于输出层中神经元的数量的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！
