“功能"的定义是什么?在神经网络中? [英] What is the definition of "feature" in neural network?

问题描述

我是神经网络的初学者.我对feature一词感到非常困惑.您能给我一个feature的定义吗?隐藏层中的神经元是特征吗?

I am a beginner of the neural network. I am very confused about the word feature. Can you give me a defintion of feature? Are the features the neurons in the hidden layers?

推荐答案

要素是输入向量的元素.特征的数量等于网络输入层中节点的数量.

The features are the elements of your input vectors. The number of features is equal to the number of nodes in the input layer of the network.

如果您使用神经网络将人分为男人或女人，则特征将包括身高，体重，头发长度等.这些特征的初始值均以米，千克等为单位，并且然后将其归一化并以零(功能内)为中心，然后呈现给系统.

If you were using a neural network to classify people as either men or women, the features would be things like height, weight, hair length etc. Each of these would have an initial value in meters, kilograms and so on, and would then be normalized and centered at zero (within-feature) prior to presentation to the system.

所以这个家伙:

高度:1.5m
重量:70kg
头发长度:0.1m

height: 1.5m
weight: 70kg
hair length: 0.1m

最初将由向量[1.5, 70, 0.1]表示，然后在进行预处理(数据集中必须有其他项...)之后，再使用[-0.2, 0.4, .05]

Would be initially represented by the vector [1.5, 70, 0.1] and then after preprocessing (there would have to be other items in the dataset...) by something like [-0.2, 0.4, .05]

字母图像的特征可能与像素的灰度值一样简单.通过处理图像并从功率谱中提取参数或查找边缘等可以生成其他特征.要了解更多信息，请查找有关图像处理和特征提取的信息.

The features of an image of a letter could be as simple as the greyscale values of pixels. Other features could be generated by processing the images and extracting parameters from power spectra, or finding edges, etc. To learn more about this, seek out information about image processing and feature extraction.

这篇关于“功能"的定义是什么?在神经网络中?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！