Dendritic neural network initialization method

The invention belongs to the field of artificial neural network optimization, and particularly relates to a dendritic neural network initialization method, which comprises the pruning of neuron dendrites, and comprises the following steps of: 1, generating a training set D from a data set by using a...

Full description

Saved in:
Bibliographic Details
Main Authors LUO XUDONG, WU LINYIN, JI LING, GE HONGYU, QIN FENG, CHEN YIZHAO, WANG HUI
Format Patent
LanguageChinese
English
Published 17.09.2021
Subjects
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
HANDLING RECORD CARRIERS
PHYSICS
PRESENTATION OF DATA
RECOGNITION OF DATA
RECORD CARRIERS
Online AccessGet full text

Cover

More Information
Summary:The invention belongs to the field of artificial neural network optimization, and particularly relates to a dendritic neural network initialization method, which comprises the pruning of neuron dendrites, and comprises the following steps of: 1, generating a training set D from a data set by using a k-fold cross validation method; 2, generating a new data set T from the training set D by using a binarization method; 3, generating a corresponding decision tree structure through an ID3 or C4.5 learning algorithm; 4, combining the paths of the decision trees with the leaf nodes marked as 1, and trimming the paths with the leaf nodes marked as 0; 5, determining the number of data layers in the dendrite neural network according to the number of paths marked as 1 in the decision tree; and 6, constructing a dendrite layer with the same classification function according to each path of the decision tree. Furthermore, the invention also comprises a classification method based on one-bit effective coding, and the initi
Bibliography:Application Number: CN202110655038