how to get best test error/accuracy with neural networks pattern recognition ?

5 visualizaciones (últimos 30 días)
casper
casper el 25 de Mzo. de 2014
Respondida: Vrushabh Bhangod el 21 de Oct. de 2018
This is Neural Network Pattern Recognition.I used a vec dataset 1*54149 and 1*54149 target and I'm trying to train my neural network to do binary classification (1 and 0).i want get best ? So please someone can help me ?. thank you in advance
clear all;
clc;
load vec; load target;
inputs = double(vec);
targets = double(target);
% Create a Pattern Recognition Network
hiddenLayerSize = 1;
%net = patternnet(hiddenLayerSize);
net = patternnet(hiddenLayerSize);
% Choose Input and Output Pre/Post-Processing Functions
% For a list of all processing functions type: help nnprocess
net.inputs{1}.processFcns = {'removeconstantrows','mapstd'};
net.outputs{2}.processFcns = {'removeconstantrows','mapstd'};
% Setup Division of Data for Training, Validation, Testing
% For a list of all data division functions type: help nndivide
net.divideFcn = 'dividerand';
net.divideMode = 'sample'; % Divide up every sample
net.divideParam.trainRatio = 50/100;
net.divideParam.valRatio = 25/100;
net.divideParam.testRatio = 25/100;
% For a list of all training functions type: help nntrain
net.trainFcn = 'trainrp';
% Choose a Performance Function
% For a list of all performance functions type: help nnperformance
net.performFcn = 'mse';
% Choose Plot Functions
% For a list of all plot functions type: help nnplot
net.plotFcns = {'plotperform','plottrainstate','ploterrhist', ...
'plotregression', 'plotfit'};
% Train the Network
[net,tr] = train(net,inputs,targets);
% Test the Network
outputs = net(inputs);
errors = gsubtract(targets,outputs);
performance = perform(net,targets,outputs);
[tpr,fpr,thresholds] = roc(targets,outputs);
% Recalculate Training, Validation and Test Performance
trainTargets = targets .* tr.trainMask{1};
valTargets = targets .* tr.valMask{1};
testTargets = targets .* tr.testMask{1};
trainPerformance = perform(net,trainTargets,outputs);
valPerformance = perform(net,valTargets,outputs);
testPerformance = perform(net,testTargets,outputs);
% View the Network
view(net)
%Plots
% Uncomment these lines to enable various plots.
figure, plotperform(tr)
figure, plottrainstate(tr)
figure, plotconfusion(targets,outputs)
figure, ploterrhist(errors)
figure, plotregression(targets,outputs)
figure, plotroc(targets,outputs)

Iniciar sesión para responder a esta pregunta.

Respuesta aceptada

Greg Heath
Greg Heath el 26 de Mzo. de 2014
Obvious:
1. plot(x,t,'.') to estimate how much training data is really needed to adequately characterize the classes AND to identify and remove or modify outliers
2. Then the short answer is to increase the number of hidden nodes, H, AND for each value of H, loop over multiple (10?) designs with different random initial weights. For examples search using
greg Hmax Ntrials
( where Hmax << Hub = -1 + ceil( (Ntrn-1)/3) ~ round(Ntrn/3) )
ADDITIONAL COMMENTS:
3. TRAINSCG is preferred for classification unless the necessary minimum value of Ntrn is huge. Then TRAINRP is preferred.
4. It may be worthwhile (OR JUST INTERESTING) to
a. Compare the default properties of both
net = trainscg % No semicolon
net = trainrp
b. See how large Ntrn can be before TRAINRP has to be used.
5. Delete or comment all statements that specify values that are already defaults (Different for SCG and RP)
6. If Ntrn is sufficiently large, Nval and Ntst will probably not add any new information.
Hope this helps.
Thank you for formally accepting my answer
Greg
  2 comentarios
casper
casper el 27 de Mzo. de 2014
Editada: casper el 27 de Mzo. de 2014
hi sir. thank you for your answer
but, i didn't understood how can i use :
greg Hmax Ntrials
( where Hmax << Hub = -1 + ceil( (Ntrn-1)/3) ~ round(Ntrn/3) )
please sir i want more detail, because i'm new in neural network.
thank you for your help
Greg Heath
Greg Heath el 28 de Mzo. de 2014
NEWSGROUP and ANSWERS designs:
I have posted jillions of double loop designs
for j = Hmin:dH:Hmax
...
for I = 1:Ntrials
...
end
end
Thee is no shortage of detail. Try the NEWSGROUP first.

Iniciar sesión para comentar.

Más respuestas (1)

Vrushabh Bhangod
Vrushabh Bhangod el 21 de Oct. de 2018
SIR, I Want a Neural Network with Logsig as the activation function and validation 0, Training % 70%, testing % 30%, learning rate 0.1, momentum coefficient and I am unable to find the accuracy. Kindly answer the earliset

Categorías

Más información sobre Sequence and Numeric Feature Data Workflows en Help Center y File Exchange.

Etiquetas

Productos

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by