Image classification method based on R-Multi-parameter PBSNLR model

Abstract

The invention discloses an image classification method based on an R-Multi-parameter PBSNLR model. The method comprises the steps: introducing a distance between a membrane voltage and a threshold value as a dynamic parameter of a weight adjustment rule on the basis of the PBSNLR model, and effectively changing a problem caused by the unique weight adjustment amplitude of the model in a training process. On the basis that the target pulse signal can be accurately learned, compared with a traditional PBSNLR model, the method has higher learning efficiency; according to the method, a dynamic threshold strategy in different time periods is adopted at the same time. the defect that ignition cannot be carried out due to insufficient film voltage accumulation at the target ignition moment possibly caused by the fact that a new threshold lower than an original threshold is used for training at the non-target ignition moment near the target ignition moment is avoided, the method has higher accuracy. Especially, in a noise environment, the learning efficiency and accuracy are obviously higher than those of other film voltage driving methods.

Description

technical field [0001] The invention relates to the field of image classification, in particular to an image classification method based on the R-Multi-parameter PBSNLR model. Background technique [0002] Perceptron is a common machine learning model, which is used to perform binary classification on the input feature vector and output a discriminant result. The supervised learning process of the spiking neural network is actually a task of controlling neurons to send pulses only at the expected ignition time during the running time by weight adjustment, and keep silent at other times. Simply put, the essence of this task is a binary classification problem that distinguishes whether the neuron model should send spikes at a specific moment. At this time, the spike neural model can be trained through the existing perceptron learning rules. PBSNLR is a typical perceptron-based supervised learning algorithm (model). It first converts the training task of the pulse sequence int...

AI Technical Summary

Problems solved by technology

However, PBSNLR cannot complete the task of online learning, and there are requirements for the number of training samples, and it needs to be trained with large samples to ensure the convergence effect

Images