Manually reproduce results from a neural network generated from Matlab
I've tried to reproduce the results I got from a trained network but was unable. Here's my script: load 'C:\Users\ZA\Documents\cosjacorr.mat' inputs = cosjacorr(:, 1:9)'; targets = cosjacorr(:, 10:13)'; numHiddenNeurons = 2; % Adjust as desired net = newpr(inputs,targets,numHiddenNeurons); net.divideParam.trainRatio = 75/100; % Adjust as desired net.divideParam.valRatio = 15/100; % Adjust as desired net.divideParam.testRatio = 10/100; % Adjust as desired net.inputs{1}.processFcns = {}; net.outputs{2}.processFcns = {}; % Train and Apply Network [net,tr] = train(net,inputs,targets); outputs = sim(net,inputs); % Plot plotconfusion(targets,outputs) I removed all pre and post processing hoping that I would be able to reproduce the results but was unsuccessful. Here's what I did in terms of replicating the network's output: y1 = tansig(net.IW{1} * input + net.b{1}); Results = tansig(net.LW{2} * y1 + net.b{2});
Kshitij Singh answered .
2025-11-20
% help newpr
% doc newpr
% Obsoleted in R2010b NNET 7.0. Last used in R2010a
close all, clear all, clc
[x t ] = simpleclass_dataset;
[ I N ] = size(x) % [ 2 1000 ]
[O N ] = size(t) % [ 4 1000]
H = 2
net = newpr(x,t,H);
net = train(net,x,t);
y = net(x);
IW = net.IW{1,1};
b1 = net.b{1};
b2 = net.b{2};
LW = net.LW{2,1};
whos
% IW 2x2 32 double
% LW 4x2 64 double
% b1 2x1 16 double
% b2 4x1 32 double
% t 4x1000 32000 double
% x 2x1000 16000 double
% y 4x1000 32000 double
B1 = repmat( b1, 1, N );
B2 = repmat( b2, 1, N );
[ xn,xsettings] = mapminmax(x);
[ tn,tsettings] = mapminmax(t);
yn = tanh( B2 + LW*tanh( B1 + IW*xn ) );
y1 = mapminmax.reverse( yn,tsettings);
dy = max(max(abs(y1-y)))