1. Glossary
Generalization :generalization (generalization ability) refers to a machine-learning ability to adapt algorithms for fresh samples.The purpose of learning is to learn the law implicit in the back of the data, the data with the same set of learning outside the law, the trained network can also give the appropriate output, the ability is called generalization.
Overfitting :over-fitting means in order to get the same assumptions the assumption becomes overly strict. Avoid over-fitting is a core task of classifier design. Typically classifier performance was evaluated using the method of increasing the amount of data and test sample set.
Extracting features : Feature extraction is a conceptual computer vision and image processing. It refers to the use of a computer to extract image information, determines whether each image point of an image feature. The results of feature extraction is to point on the image is divided into different subsets, which subsets are often of isolated dots, a continuous curve or a continuous area.