DeepAI
Log In Sign Up

Research on a New Convolutional Neural Network Model Combined with Random Edges Adding

03/17/2020
by   Xuanyu Shu, et al.
6

It is always a hot and difficult point to improve the accuracy of convolutional neural network model and speed up its convergence. Based on the idea of small world network, a random edge adding algorithm is proposed to improve the performance of convolutional neural network model. This algorithm takes the convolutional neural network model as a benchmark, and randomizes backwards and cross-layer connections with probability p to form a new convolutional neural network model. The proposed idea can optimize the cross layer connectivity by changing the topological structure of convolutional neural network, and provide a new idea for the improvement of the model. The simulation results based on Fashion-MINST and cifar10 data set show that the model recognition accuracy and training convergence speed are greatly improved by random edge adding reconstructed models with aprobability p = 0.1.

READ FULL TEXT

page 1

page 2

page 3

page 4

01/14/2020

Convolutional Mean: A Simple Convolutional Neural Network for Illuminant Estimation

We present Convolutional Mean (CM) - a simple and fast convolutional neu...
12/03/2017

Automatic Recognition of Coal and Gangue based on Convolution Neural Network

We designed a gangue sorting system,and built a convolutional neural net...
12/23/2020

Convolutional Neural Network for Elderly Wandering Prediction in Indoor Scenarios

This work proposes a way to detect the wandering activity of Alzheimer's...
07/28/2019

Learning Wear Patterns on Footwear Outsoles Using Convolutional Neural Networks

Footwear outsoles acquire characteristics unique to the individual weari...
02/24/2018

Convolutional Neural Networks combined with Runge-Kutta Methods

A convolutional neural network for image classification can be construct...
01/17/2022

Growing Neural Network with Shared Parameter

We propose a general method for growing neural network with shared param...