11-04-2017, 10:51 AM
An artificial neural network (NN for short) is a classifier. In supervised machine learning, grading is one of the most prominent problems. The objective is to classify objects into classes that are defined a priori (terminology that should not be confused with object-oriented programming). The classification has a wide field of applications, for example:
• In image processing we can try to distinguish images representing different classes (classes) of objects (eg cars, bicycles, buildings, etc.)
• In natural language processing (NLP), we can try to classify texts into categories (for example, distinguish texts that speak about politics, sports, culture, etc.)
• In financial transaction processing, we can try to decide if a new transaction is legitimate or fraudulent.
The term "supervised" refers to the fact that the algorithm has been previously trained with "tagged" examples for each category (ie examples whose classes are known by the NN) to learn how to classify new, invisible ones in the future.
• In image processing we can try to distinguish images representing different classes (classes) of objects (eg cars, bicycles, buildings, etc.)
• In natural language processing (NLP), we can try to classify texts into categories (for example, distinguish texts that speak about politics, sports, culture, etc.)
• In financial transaction processing, we can try to decide if a new transaction is legitimate or fraudulent.
The term "supervised" refers to the fact that the algorithm has been previously trained with "tagged" examples for each category (ie examples whose classes are known by the NN) to learn how to classify new, invisible ones in the future.
