Why is predicting the output of a trained neural network by using

Question

Why is predicting the output of a trained neural network by using "net/sim" different than manually calculating the output using the network weights, biases and transfer functions? Refer to the following example:   %%create random data rng(1); xdata = rand(5,100); ydata = rand(1,100); %%fit a forward network nlayersize = 10; net = feedforwardnet(nlayersize); net.trainParam.showWindow = false; net = train(net,xdata,ydata); net.layers{1}.transferFcn %%calculate the model output at a new point xNew = rand(5,1); y1 = net(xNew); % can use sim as well %%manually calculate model output IW = net.IW{1}; LW = net.LW{2,1}; b = net.b; y2 = IW*xNew+b{1}; y2 = tansig(y2); y2 = LW*y2+b{2}; dy = y1-y2 "dy" is not zero but it should be.

John Williams · Accepted Answer

The difference between the network predictions using "net/sim" functions and manually computing the prediction using the code in the question is in the "minmax" processing that most neural networks automatically apply to the input and target (output) data. You can refer to the following documentation link for the "mapminmax" function which is used for this pre-processing of the training data:
 

The settings for this pre-processing steps are stored in "net.inputs{1}.processSettings{1}" for the input pre-processing and "net.outputs{2}.processSettings{1}" for the output pre-processing. So, if you change the code to the following you should obtain a &lsquo;dy&rsquo; difference of practically zero (something of the order of 10^-16):
 

xNew = rand(5,1);

y1 = net(xNew);

 

xNew = mapminmax('apply', xNew , net.inputs{1}.processSettings{1}); % apply input pre-processing

 

IW = net.IW{1};

LW = net.LW{2, 1};

b = net.b;

 

y2 = IW*xNew+b{1};

y2 = tansig(y2);

 

y2 = LW*y2+b{2};

y2 = mapminmax('reverse', y2, net.outputs{2}.processSettings{1}); % reverse the output pre-processing

dy = y1 - y2

Why is predicting the output of a trained neural network by using

Need a Custom Version or Complete Simulation for This Problem?

How to change the activation function in ANN model created using toolbox

How do I build TensorFlow Lite for Deep Learning C++ code generation and deployment?

How to train labels for image blocks using neural network?

Using a python trained neural network

How can we train images in matlab using artificial neural network?

How to predict next value using time series?

IEEE 13-BUS Hybrid AC & DC Power Distribution System using MATLAB Simulink

Adaptive Path Planning and Collision Avoidance for Autonomous Vehicles on Unstructured Indian Roads

Lithium-Ion Battery Electro-Thermal Modeling and Cooling Analysis in MATLAB

Get a Free Consultation or a Sample Assignment Review!