In simple terms, is to let the computer through the program to help humans do some large-scale data identification, sorting, law summary and other human beings do more time-consuming things.
The classic machine learning scenario is a spam sorting system, with a classifier that can sort incoming mail into “regular mail” and “junk mail.” But the criteria for spam are not given at the beginning of the program, but after the classifier is fed a large amount of spam. The classification of spam samples by the various characteristics of statistics and induction and then obtained.
In this training process, a large number of messages labeled as spam are given to the classifier, which is called training samples. The classifier collects statistics and summarizes the characteristics of spam samples, which is called training. The judgment criteria summarized are called classification model. At the same time, we will also take some other “ordinary mail” and “junk mail” to the classifier, and ask it to try to classify according to the classification model just summarized, to see the accuracy of its classification, this step is called verification.
So machine learning is the process by which computers learn to distinguish things correctly.
Beijing Boshi Technology Co., Ltd. is a technical education service company specializing in online education software development and post-production video