check the category in which given data belonging to.

Question

shrisha tv 2018-7-18

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/410848-check-the-category-in-which-given-data-belonging-to

I have trained the given dataset into 4 different category target using artificial neural network tool(nprtool). now I have to check the new data with trained set and display the category of the data belonging to.please someone help me to solve the problem. here is the code, i didn't understand the first line of code (i.e X,~,~) what it refers. where i have to give new sample as input in this network.

if true
 if true
  function [Y,Xf,Af] = myNeuralNetworkFunction(X,~,~)
%MYNEURALNETWORKFUNCTION neural network simulation function.
%
% Generated by Neural Network Toolbox function genFunction, 18-Jul-2018 10:37:01.
%
% [Y] = myNeuralNetworkFunction(X,~,~) takes these arguments:
%
%   X = 1xTS cell, 1 inputs over TS timesteps
%   Each X{1,ts} = 2988xQ matrix, input #1 at timestep ts.
%
% and returns:
%   Y = 1xTS cell of 1 outputs over TS timesteps.
%   Each Y{1,ts} = 4xQ matrix, output #1 at timestep ts.
%
% where Q is number of samples (or series) and TS is the number of timesteps.

%#ok<*RPMT0>

% ===== NEURAL NETWORK CONSTANTS =====

% Input 1 x1_step1.xoffset = [36.6032980307133;36.597744090219;0.158385245033053;1.31643417503494;36.6049269523476;-1.37584123238539;11.0299405848326;12.504831642294;0.288194444444444;0.332638888888889;28.8194444444444;33.2638888888889;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0.770633759029644;0.768310906303693;0.766707167608389;0.764830097334775;0.762377934568729;0.762331857496514;0.763674710343093]; x1_step1.ymin = -1;

% Layer 1 b1 = [1.3994768477631403;-1.0903884727432014;-0.78011654543485587;0.46705708446426597;0.16258381065370511;0.15440406609565069;-0.46920117774766312;-0.77810609521143459;-1.0906776883213438;-1.4018315002684629]; IW1_1 = [-0.033467156180729256 -0.028666674896511351 -0.015836935383914983 -0.022354599237305886 0.034889064440252859 -0.0064257682289154327 -0.035010735784467298 -0.026398464854472514 -0.014592920844527422 0.0048257790054789321 0.018154687124502519 -0.03867327363872404 -0.023292923677313667 0.025188775694068535 0.045099731617422686 -0.030543785712876966 0.03771919987654563 0.027258279939602156 0.015255478168750499 0.037858970851422521 0.027504725538651929 0.037368094581401889];

% Layer 2 b2 = [0.70447808985535643;-0.84986964370713036;-0.22125627190808969;0.38507031312787227]; LW2_1 = [0.32190735802132342 -0.21033440896068742 0.37105847152081861 -0.34423404255830287 -0.60160268808835204 0.53680797032043304 0.084849606402260497 -0.01577021545359597 0.97526564139699645 -0.93082198599126553;-0.09009035442617104 -0.77884663695955614 0.071553227629483948 0.1605495822863553 -0.75867661703141376 0.84203715319603523 -0.1514908834679804 -0.45805124784681861 -0.48046860963249433 0.24476893884595838];

% ===== SIMULATION ========

% Format Input Arguments isCellX = iscell(X); if ~isCellX X = {X}; end

% Dimensions TS = size(X,2); % timesteps if ~isempty(X) Q = size(X{1},2); % samples/series else Q = 0; end

% Allocate Outputs Y = cell(1,TS);

% Time loop for ts=1:TS

    % Input 1
    Xp1 = mapminmax_apply(X{1,ts},x1_step1);
    % Layer 1
    a1 = tansig_apply(repmat(b1,1,Q) + IW1_1*Xp1);
    % Layer 2
    a2 = softmax_apply(repmat(b2,1,Q) + LW2_1*a1);
    % Output 1
    Y{1,ts} = a2;
end

% Final Delay States Xf = cell(1,0); Af = cell(2,0);

% Format Output Arguments if ~isCellX Y = cell2mat(Y); end end

% ===== MODULE FUNCTIONS ========

% Map Minimum and Maximum Input Processing Function function y = mapminmax_apply(x,settings) y = bsxfun(@minus,x,settings.xoffset); y = bsxfun(@times,y,settings.gain); y = bsxfun(@plus,y,settings.ymin); end

% Competitive Soft Transfer Function function a = softmax_apply(n,~) if isa(n,'gpuArray') a = iSoftmaxApplyGPU(n); else a = iSoftmaxApplyCPU(n); end end function a = iSoftmaxApplyCPU(n) nmax = max(n,[],1); n = bsxfun(@minus,n,nmax); numerator = exp(n); denominator = sum(numerator,1); denominator(denominator == 0) = 1; a = bsxfun(@rdivide,numerator,denominator); end function a = iSoftmaxApplyGPU(n) nmax = max(n,[],1); numerator = arrayfun(@iSoftmaxApplyGPUHelper1,n,nmax); denominator = sum(numerator,1); a = arrayfun(@iSoftmaxApplyGPUHelper2,numerator,denominator); end function numerator = iSoftmaxApplyGPUHelper1(n,nmax) numerator = exp(n - nmax); end function a = iSoftmaxApplyGPUHelper2(numerator,denominator) if (denominator == 0) a = numerator; else a = numerator ./ denominator; end end

% Sigmoid Symmetric Transfer Function function a = tansig_apply(n,~) a = 2 ./ (1 + exp(-2*n)) - 1; end endif true function [Y,Xf,Af] = myNeuralNetworkFunction(X,~,~) %MYNEURALNETWORKFUNCTION neural network simulation function. % % Generated by Neural Network Toolbox function genFunction, 18-Jul-2018 10:37:01. % % [Y] = myNeuralNetworkFunction(X,~,~) takes these arguments: % % X = 1xTS cell, 1 inputs over TS timesteps % Each X{1,ts} = 2988xQ matrix, input #1 at timestep ts. % % and returns: % Y = 1xTS cell of 1 outputs over TS timesteps. % Each Y{1,ts} = 4xQ matrix, output #1 at timestep ts. % % where Q is number of samples (or series) and TS is the number of timesteps.

%#ok<*RPMT0>

% ===== NEURAL NETWORK CONSTANTS =====

% Input 1 x1_step1.xoffset = [36.6032980307133;36.597744090219;0.158385245033053;1.31643417503494;36.6049269523476;-1.37584123238539;11.0299405848326;12.504831642294;0.288194444444444;0.332638888888889;28.8194444444444;33.2638888888889;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;0;036.607812674681;36.602736524947;36.5999981547226;36.6008968560731;36.6032980307133]; x1_step1.gain = [0.763674710343093;0.849017249009819;2.71347549410056;0.372434551277165;0.76192577149486;;0.770633759029644;0.768310906303693;0.766707167608389;0.764830097334775;0.762377934568729;0.762331857496514;0.763674710343093]; x1_step1.ymin = -1;

% Layer 1 b1 = [1.3994768477631403;-1.0903884727432014;-0.78011654543485587;0.46705708446426597;0.16258381065370511;0.15440406609565069;-0.46920117774766312;-0.77810609521143459;-1.0906776883213438;-1.4018315002684629]; IW1_1 = [-0.033467156180729256 -0.028666674896511351 -0.015836935383914983 -0.022354599237305886 0.034889064440252859 -0.0064257682289154327 -0.035010735784467298 -0.026398464854472514 -0.014592920844527422 -0.037192638242207338 -0.030543785712876966 0.03771919987654563 0.027258279939602156 0.015255478168750499 0.037858970851422521 0.027504725538651929 0.037368094581401889];

% Layer 2 b2 = [0.70447808985535643;-0.84986964370713036;-0.22125627190808969;0.38507031312787227]; LW2_1 = [0.32190735802132342 -0.21033440896068742 0.37105847152081861 -0.34423404255830287 -0.60160268808835204 0.53680797032043304 0.084849606402260497 -0.01577021545359597 0.97526564139699645 -0.93082198599126553;-0.09009035442617104 -0.77884663695955614 0.071553227629483948 0.1605495822863553 -0.9780966231383238 -0.75867661703141376 0.84203715319603523 -0.1514908834679804 -0.45805124784681861 -0.48046860963249433 0.24476893884595838];

% ===== SIMULATION ========

% Format Input Arguments isCellX = iscell(X); if ~isCellX X = {X}; end

% Dimensions TS = size(X,2); % timesteps if ~isempty(X) Q = size(X{1},2); % samples/series else Q = 0; end

% Allocate Outputs Y = cell(1,TS);

% Time loop for ts=1:TS

    % Input 1
    Xp1 = mapminmax_apply(X{1,ts},x1_step1);
    % Layer 1
    a1 = tansig_apply(repmat(b1,1,Q) + IW1_1*Xp1);
    % Layer 2
    a2 = softmax_apply(repmat(b2,1,Q) + LW2_1*a1);
    % Output 1
    Y{1,ts} = a2;
end

% Final Delay States Xf = cell(1,0); Af = cell(2,0);

% Format Output Arguments if ~isCellX Y = cell2mat(Y); end end

% ===== MODULE FUNCTIONS ========

% Map Minimum and Maximum Input Processing Function function y = mapminmax_apply(x,settings) y = bsxfun(@minus,x,settings.xoffset); y = bsxfun(@times,y,settings.gain); y = bsxfun(@plus,y,settings.ymin); end

% Competitive Soft Transfer Function function a = softmax_apply(n,~) if isa(n,'gpuArray') a = iSoftmaxApplyGPU(n); else a = iSoftmaxApplyCPU(n); end end function a = iSoftmaxApplyCPU(n) nmax = max(n,[],1); n = bsxfun(@minus,n,nmax); numerator = exp(n); denominator = sum(numerator,1); denominator(denominator == 0) = 1; a = bsxfun(@rdivide,numerator,denominator); end function a = iSoftmaxApplyGPU(n) nmax = max(n,[],1); numerator = arrayfun(@iSoftmaxApplyGPUHelper1,n,nmax); denominator = sum(numerator,1); a = arrayfun(@iSoftmaxApplyGPUHelper2,numerator,denominator); end function numerator = iSoftmaxApplyGPUHelper1(n,nmax) numerator = exp(n - nmax); end function a = iSoftmaxApplyGPUHelper2(numerator,denominator) if (denominator == 0) a = numerator; else a = numerator ./ denominator; end end

% Sigmoid Symmetric Transfer Function function a = tansig_apply(n,~) a = 2 ./ (1 + exp(-2*n)) - 1; end end

and also please help me to find out what is the meaning of this code. because I didn't understand the some part of the code what actually it is doing. thank you in advance.