A single-layer image classification method based on delay mechanism

Abstract

The invention discloses a single-layer image classification method based on a delay mechanism, belonging to the technical field of image processing. The method comprises the following steps: S1, constructing an image classification model; S2, using an image set to train the image classification model, and obtaining a trained image Image classification model; S3. Use the image classification model completed by training to classify the image to obtain the category of the image; the image classification model includes a feature extraction unit, a pulse delay coding unit and a single-layer classifier connected in sequence; the present invention solves the problem of Tempotron learning Algorithms only rely on adjusting synaptic weights, which leads to the problem that the learning effect is highly susceptible to interference.

Description

technical field

[0001] The invention relates to the technical field of image processing, in particular to a single-layer image classification method based on a delay mechanism. Background technique

[0002] Tempotron is one of the earliest algorithms to describe the changes in the membrane voltage of spiking neurons, and it pioneered the description of the basic characteristics of a class of algorithms based on membrane voltage drive. The adjustment of synaptic weights is only related to the maximum membrane voltage, and only the influence of threshold and kernel function needs to be considered. The role of Tempotron in spiking neural networks is similar to the basic role of perceptrons. The simplicity of the Tempotron algorithm leads it to only solve binary classification problems. However, many researchers have also made a lot of innovations and improvements based on the Tempotron algorithm.

[0003] The Tempotron algorithm has two main defects: one is that the postsyna...

Images