What is the definition of “feature” in neural network?

Question

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

Answer 1

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.

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.

So this guy:

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

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]

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.

Answer 2

Features in a neural network are the variables or attributes in your data set. You usually pick a subset of variables that can be used as good predictors by your model. So in a neural network, the features would be the input layer, not the hidden layer nodes. The output is whatever variable (or variables) you're trying to predict.