MATLAB: Inverse transformation for Sim

rbfsim

We generate the neural network object. We use the sim(net,i/p) and see how the network predicts for the given input vector. Is there any inverse transformation function for 'sim'. given the network object and output, see what will be the input vector.

Best Answer

No.

However, you can train another net that will take a target as input and estimate the original input.

Obviously, the restoration will improve as the number of uncorrelated target values increase.

Hope this helps.

Greg

Related Solutions

MATLAB: How to train ann with multiple input data

% Create a network (i have used feed-forward backpropagation)
net = newff(TrainFeatures, Trainlabels, num_of_hidden_Neurons);
% Set Train, Test and Validation Ration
net.divideParam.trainRatio = 70/100;  
net.divideParam.valRatio = 15/100;  
net.divideParam.testRatio = 15/100; 
net = train(net, TrainFeatures, Trainlabels);

MATLAB: Inverse Dynamics is SimMechanics

SimMechanics First Generation can handle inverse dynamics (specifying motion and measure force/torques).

Since R2012a, SimMechanics Second Generation exists, but does not support inverse dynamics up to R2013a. We are working hard to make inverse dynamics available as soon as possible.

Best Answer

Related Solutions

MATLAB: How to train ann with multiple input data

MATLAB: Inverse Dynamics is SimMechanics

Related Question