1.完整项目描述和程序获取
>面包多安全交易平台:https://mbd.pub/o/bread/Y56Wmp1t
>如果链接失效，可以直接打开本站店铺搜索相关店铺：
>如果链接失效，程序调试报错或者项目合作也可以加微信或者QQ联系。
2.部分仿真图预览
3.算法概述
卷积神经网络（Convolutional Neural Networks, CNN）是一类包含卷积计算且具有深度结构的前馈神经网络（Feedforward Neural Networks），是深度学习（deep learning）的代表算法之一 。卷积神经网络具有表征学习（representation learning）能力，能够按其阶层结构对输入信息进行平移不变分类（shift-invariant classification），因此也被称为“平移不变人工神经网络（Shift-Invariant Artificial Neural Networks, SIANN）” 。
4.部分源码
targetD=categorical([0;0;1;1]);
%% Define Network Architecture
% Define the convolutional neural network architecture.
layers = [
imageInputLayer([22 5 3]) % 22X5X3 refers to number of features per sample
convolution2dLayer(5,16,'Padding','same') % 5x5 filtr is used, u can try 3x3 filtr also
reluLayer % activation function
% i have not used any pooling layer here, since small data size
% if u giving big data use pooling layer
% pooling layer reduces size of the matrix
fullyConnectedLayer(384) % 384 refers to number of neurons in next FC hidden layer
fullyConnectedLayer(384) % 384 refers to number of neurons in next FC hidden layer
fullyConnectedLayer(2) % 2 refers to number of neurons in next output layer (number of output classes)
softmaxLayer
classificationLayer];
.............................................................
net = trainNetwork(trainD,targetD',layers,options);
predictedLabels = classify(net,trainD)'
A_244
