Ganglion differentiation-based incremental target identification system

Abstract

The invention discloses a ganglion differentiation-based incremental target identification system. The system is composed of a low hidden layer, a ganglion layer, a high hidden layer and a classifier, wherein the ganglion layer is located between the low hidden layer and the high hidden layer; ganglions of the ganglion layer extract a sample characteristic law, and through activation and differentiation of the ganglions, corresponding independent characteristic sets are formed in the high hidden layer and characteristic memory of samples is formed; a quantity of the characteristic sets of the high hidden layer is variable; newly added ganglions form new memory for new samples, and the characteristic sets of the high hidden layer are adaptively updated, so that incremental target identification is realized; the ganglions refer to neural network nodes used for representing a group of samples with similar distribution laws, and when an input sample characteristic parameter is greater than an activation threshold, the ganglions are activated and form the independent characteristic sets in the high hidden layer; when the activity of the activated ganglions is lower than a threshold, the ganglions die; and different ganglions are activated for the samples with different characteristics, and ganglions are newly added.

Description

technical field [0001] The invention belongs to the field of target recognition, in particular to an incremental target recognition system based on ganglion differentiation. Background technique [0002] The early deep neural network is end-to-end, and the network structure remains unchanged during the training process, which is the process of learning network parameters. When the training set is complete and the network depth is sufficient, it can theoretically express arbitrarily complex original data. In many practical applications, the complete data set cannot be obtained at one time, so the learning algorithm also needs to be a continuous process. For example, in software products such as image search and photo shopping, pre-obtain the existing product image set, and use the deep neural network to find the closest top items for the input image as the recommendation result. However, when inputting a newly developed product image with a new appearance, although the trai...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to solve the following technical problems. The existing recognition method has a solidified network structure, is only applicable to static data sets, repeated learning in a massive data environment, and has poor anti-noise ability

Images