Method, apparatus, and program for evolving neural network architectures to detect content in media information

摘要

A method for operating a neural network (300), and a program and apparatus (2; 4) that operate in accordance with the method. The method comprises the steps of applying data indicative of predetermined content, derived from an electronic signal including a representation of the predetermined content, to an input of at least one neural network (300), to cause the at least one network (300) to generate at least one output indicative of either a detection or a non-detection of the predetermined content. Each neural network (300) has an architecture specified by at least one corresponding parameter. The method also comprises a step of evolving the at least one parameter to modify the architecture of the at least one neural network (300), based on the at least one output, to increase an accuracy at which that at least one neural network (300) detects the predetermined content indicated by the data.