Multilayer-perceptron training method based on bee colony algorithm with learning factor

A particle swarm algorithm and population technology, applied in the field of neural computing and intelligent optimization, can solve the problems of high complexity, high dimension, multi-modal optimization, high sensitivity of initial weights, easy to fall into local optimum, etc., to enhance the global Search ability, avoid premature convergence, enhance the effect of adaptive optimization ability

Inactive Publication Date: 2014-09-17
JIANGNAN UNIV
View PDF0 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

As far as training is concerned, the BP algorithm based on gradient descent is the most commonly used algorithm for training multilayer perceptrons, but it often encounters some problems when using it, such as high sensitivity of initial weights during training, slow convergence rate, and easy to fall into local best
Therefore, some new

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Multilayer-perceptron training method based on bee colony algorithm with learning factor
  • Multilayer-perceptron training method based on bee colony algorithm with learning factor
  • Multilayer-perceptron training method based on bee colony algorithm with learning factor

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033]In order to better understand the technical solution of the present invention, the implementation manner is further described in detail below, and an application example is used to illustrate the specific implementation manner, but is not limited thereto.

[0034] Embodiment: In order to evaluate the performance of the algorithm of the present invention, take sinx function as example here, utilize multi-layer perceptron to carry out fitting training to this function, the input layer of multi-layer perceptron has 1 neuron, and hidden layer has 10 neurons There is one neuron in the output layer, and the network training results can be obtained through computer simulation experiments. The working process of the inventive method is as figure 1 As shown, the specific implementation method can be divided into the following steps:

[0035] Step1: Generate 26 sets of training data at equal intervals on the interval [-2π, 2π] by the function sin x, m=62 sets of test data (U k ,...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a multilayer-perceptron training method based on a bee colony algorithm with a learning factor. In the method, an idea of asynchronous adjustment of the learning factor is introduced to update a nectar source position of following bees so that the self-adaptive optimization capability of a bee colony is strengthened and single extreme values and a global extreme value of the colony are used to improve a search mode in the manual bee colony algorithm so that search efficiency and performance are optimized so as to achieve an optimal optimization effect of an initial weight and threshold of a multilayer perceptron and improve the predication precision of the multilayer perceptron.

Description

technical field [0001] The invention relates to the fields of neural calculation and intelligent optimization, in particular to a multi-layer perceptron training method based on bee colony algorithm with learning factors. Background technique [0002] In the past two decades, artificial neural networks, especially multi-layer perceptrons trained with BP algorithm, have been widely used in various fields. Theory has proved that by choosing appropriate weights and activation functions, multilayer perceptrons trained with nonlinear functions can approximate and accurately generalize almost any continuous function without considering the prior assumptions of the data distribution. It can simulate highly nonlinear functions and can be trained to generalize accurately on unused new data. Like many neural network models, multilayer perceptrons must be trained to gain fit, prediction, and more. As far as training is concerned, the BP algorithm based on gradient descent is the most...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06N3/00G06N3/02
Inventor 楼旭阳
Owner JIANGNAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap