Neural Network Activation function

I have 3 input hidden layer and 1 output layer.

I want to set the activation function for input layer as purelin

and output layer as tansig/purelin in 2 different models.

How can I set the above conditions?

Answer 1

[Chunru]

net = feedforwardnet([10 20]);     % 2 hidden, 1 output layers

% specify the transfer function as you want
% Usually, layer1 will not be pureli
net.layers{1}.transferFcn = 'tansig';   % hidden layer 1
net.layers{2}.transferFcn = 'tansig';    % hidden layer 2
net.layers{3}.transferFcn = 'purelin';    % output layer

net

net =

    Neural Network
 
              name: 'Feed-Forward Neural Network'
          userdata: (your custom info)
 
    dimensions:
 
         numInputs: 1
         numLayers: 3
        numOutputs: 1
    numInputDelays: 0
    numLayerDelays: 0
 numFeedbackDelays: 0
 numWeightElements: 230
        sampleTime: 1
 
    connections:
 
       biasConnect: [1; 1; 1]
      inputConnect: [1; 0; 0]
      layerConnect: [0 0 0; 1 0 0; 0 1 0]
     outputConnect: [0 0 1]
 
    subobjects:
 
             input: Equivalent to inputs{1}
            output: Equivalent to outputs{3}
 
            inputs: {1x1 cell array of 1 input}
            layers: {3x1 cell array of 3 layers}
           outputs: {1x3 cell array of 1 output}
            biases: {3x1 cell array of 3 biases}
      inputWeights: {3x1 cell array of 1 weight}
      layerWeights: {3x3 cell array of 2 weights}
 
    functions:
 
          adaptFcn: 'adaptwb'
        adaptParam: (none)
          derivFcn: 'defaultderiv'
         divideFcn: 'dividerand'
       divideParam: .trainRatio, .valRatio, .testRatio
        divideMode: 'sample'
           initFcn: 'initlay'
        performFcn: 'mse'
      performParam: .regularization, .normalization
          plotFcns: {'plotperform', 'plottrainstate', 'ploterrhist',
                    'plotregression'}
        plotParams: {1x4 cell array of 4 params}
          trainFcn: 'trainlm'
        trainParam: .showWindow, .showCommandLine, .show, .epochs,
                    .time, .goal, .min_grad, .max_fail, .mu, .mu_dec,
                    .mu_inc, .mu_max
 
    weight and bias values:
 
                IW: {3x1 cell} containing 1 input weight matrix
                LW: {3x3 cell} containing 2 layer weight matrices
                 b: {3x1 cell} containing 3 bias vectors
 
    methods:
 
             adapt: Learn while in continuous use
         configure: Configure inputs & outputs
            gensim: Generate Simulink model
              init: Initialize weights & biases
           perform: Calculate performance
               sim: Evaluate network outputs given inputs
             train: Train network with examples
              view: View diagram
       unconfigure: Unconfigure inputs & outputs