我试图创建一个神经网络 - 非线性时间序列 NARX模型
算法我的输入是
1-2D矩阵（x，y）
2 - 另一个2D矩阵（x，y）
并且目标是此2D矩阵（x，y）
中的实际精确值首先我搜索了一下，然后用 MATLAB 模拟了这个网络，我有一个
我将在 DOWN
中显示效果良好然而，我想实现这个模型＆＃34; NARX MODEL ＆＃34;在 PYTHON
我搜索了（NARX MODEL）的算法，我没有得到我想要的结果：
1 - 有人给我任何参考，网站， BOOKs ，视频系列
2 - 或向我显示 WAY 以正确搜索此特定任务
3 - 或者给我一个步骤，用python 等效制作代码到** MATLAB＆＃34; NARX
源代码和功能＆＃34; **
这是CODE MATLAB：
% Solve an Autoregression Problem with External Input with a NARX Neural Network
% Script generated by NTSTOOL
% Created Wed Nov 09 20:28:50 EET 2016
%
% This script assumes these variables are defined:
%
% input- input time series.
% output- feedback time series.
inputSeries = tonndata(input,true,false);
targetSeries = tonndata(output,true,false);
% Create a Nonlinear Autoregressive Network with External Input
inputDelays = 1:2;
feedbackDelays = 1:2;
hiddenLayerSize = 10;
net = narxnet(inputDelays,feedbackDelays,hiddenLayerSize);
% Choose Input and Feedback Pre/Post-Processing Functions
% Settings for feedback input are automatically applied to feedback output
% For a list of all processing functions type: help nnprocess
% Customize input parameters at: net.inputs{i}.processParam
% Customize output parameters at: net.outputs{i}.processParam
net.inputs{1}.processFcns = {'removeconstantrows','mapminmax'};
net.inputs{2}.processFcns = {'removeconstantrows','mapminmax'};
% Prepare the Data for Training and Simulation
% The function PREPARETS prepares timeseries data for a particular network,
% shifting time by the minimum amount to fill input states and layer states.
% Using PREPARETS allows you to keep your original time series data unchanged, while
% easily customizing it for networks with differing numbers of delays, with
% open loop or closed loop feedback modes.
[inputs,inputStates,layerStates,targets] = preparets(net,inputSeries, {},targetSeries);
% Setup Division of Data for Training, Validation, Testing
% The function DIVIDERAND randomly assigns target values to training,
% validation and test sets during training.
% For a list of all data division functions type: help nndivide
net.divideFcn = 'dividerand'; % Divide data randomly
% The property DIVIDEMODE set to TIMESTEP means that targets are divided
% into training, validation and test sets according to timesteps.
% For a list of data division modes type: help nntype_data_division_mode
net.divideMode = 'value'; % Divide up every value
net.divideParam.trainRatio = 70/100;
net.divideParam.valRatio = 15/100;
net.divideParam.testRatio = 15/100;
% Choose a Training Function
% For a list of all training functions type: help nntrain
% Customize training parameters at: net.trainParam
net.trainFcn = 'trainlm'; % Levenberg-Marquardt
% Choose a Performance Function
% For a list of all performance functions type: help nnperformance
% Customize performance parameters at: net.performParam
net.performFcn = 'mse'; % Mean squared error
% Choose Plot Functions
% For a list of all plot functions type: help nnplot
% Customize plot parameters at: net.plotParam
net.plotFcns = {'plotperform','plottrainstate','plotresponse', ...
'ploterrcorr', 'plotinerrcorr'};
% Train the Network
[net,tr] = train(net,inputs,targets,inputStates,layerStates);
% Test the Network
outputs = net(inputs,inputStates,layerStates);
errors = gsubtract(targets,outputs);
performance = perform(net,targets,outputs)
% Recalculate Training, Validation and Test Performance
trainTargets = gmultiply(targets,tr.trainMask);
valTargets = gmultiply(targets,tr.valMask);
testTargets = gmultiply(targets,tr.testMask);
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, plotregression(targets,outputs)
%figure, plotresponse(targets,outputs)
%figure, ploterrcorr(errors)
%figure, plotinerrcorr(inputs,errors)
% Closed Loop Network
% Use this network to do multi-step prediction.
% The function CLOSELOOP replaces the feedback input with a direct
% connection from the outout layer.
netc = closeloop(net);
netc.name = [net.name ' - Closed Loop'];
view(netc)
[xc,xic,aic,tc] = preparets(netc,inputSeries,{},targetSeries);
yc = netc(xc,xic,aic);
closedLoopPerformance = perform(netc,tc,yc)
% Early Prediction Network
% For some applications it helps to get the prediction a timestep early.
% The original network returns predicted y(t+1) at the same time it is given y(t+1).
% For some applications such as decision making, it would help to have predicted
% y(t+1) once y(t) is available, but before the actual y(t+1) occurs.
% The network can be made to return its output a timestep early by removing one delay
% so that its minimal tap delay is now 0 instead of 1. The new network returns the
% same outputs as the original network, but outputs are shifted left one timestep.
nets = removedelay(net);
nets.name = [net.name ' - Predict One Step Ahead'];
view(nets)
[xs,xis,ais,ts] = preparets(nets,inputSeries,{},targetSeries);
ys = nets(xs,xis,ais);
earlyPredictPerformance = perform(nets,ts,ys)
以下是输入
这是x坐标
1 4 7 9 11 17 14 16 18 19
这是y坐标
1 2 4 6 7 8 10 10 13 14
这是另一个x坐标
1 7 10 13 16 18 19 23 24 25
这是另一个y坐标
1 5 7 9 12 14 16 17 19 20
这是目标
这是实际的x坐标
1 4 5 8 9 15 17 18 20 22
这是实际的y坐标
1 1 4 7 8 10 13 14 18 20
并且结果对于两个输入中的这个大错误都足够好与输出相比 但是通过改变神经，我们可以增强这个输出
[5.00163468043085;3.99820942369434]
[8.00059395052246;6.99872447652641]
[11.5625431537178;8.00040094120297]
[14.9982223917152;9.24359668634943]
[19.3511330333522;13.0001065644369]
[18.4627579643821;13.9999624796494]
[20.0004073095041;17.9997197490528]
[22.0004822590849;19.9997852867243]
希望这一点足够明确
提前致谢
答案 0 :(得分：1)