1
برق و الکترونیک::
استخراج ویژگی
This is called feature extraction.
• Feature extraction: combining existing features to produce a more useful one (as we saw earlier, dimensionality reduction algorithms can help).
In this chapter we will explain in more depth how autoencoders work, what types of constraints can be imposed, and how to implement them using TensorFlow, whether it is for dimensionality reduction, feature extraction, unsupervised pretraining, or as generative models.
In a 2008 paper,3 Pascal Vincent et al. showed that autoencoders could also be used for feature extraction.
Another kind of constraint that often leads to good feature extraction is sparsity: by adding an appropriate term to the cost function, the autoencoder is pushed to reduce the number of active neurons in the coding layer.
واژگان شبکه مترجمین ایران