4
$\begingroup$

NOTE: This question was first posted in cross-validated website but I was instructed to move it off that website as it was not a good fit.

I am new in implementation of machine learning, neural network in python. I am trying to implement patternet in python as it is in MATLAB; more specifically to keep the network configuration settings. Below is what I get when I use paternet(10):

    Neural Network

              name: 'Pattern Recognition Neural Network'
          userdata: (your custom info)

    dimensions:

         numInputs: 1
         numLayers: 2
        numOutputs: 1
    numInputDelays: 0
    numLayerDelays: 0
 numFeedbackDelays: 0
 numWeightElements: 230
        sampleTime: 1

    connections:

       biasConnect: [1; 1]
      inputConnect: [1; 0]
      layerConnect: [0 0; 1 0]
     outputConnect: [0 1]

    subobjects:

             input: Equivalent to inputs{1}
            output: Equivalent to outputs{2}

            inputs: {1x1 cell array of 1 input}
            layers: {2x1 cell array of 2 layers}
           outputs: {1x2 cell array of 1 output}
            biases: {2x1 cell array of 2 biases}
      inputWeights: {2x1 cell array of 1 weight}
      layerWeights: {2x2 cell array of 1 weight}

    functions:

          adaptFcn: 'adaptwb'
        adaptParam: (none)
          derivFcn: 'defaultderiv'
         divideFcn: 'divideind'
       divideParam: .trainInd, .valInd, .testInd
        divideMode: 'sample'
           initFcn: 'initlay'
        performFcn: 'crossentropy'
      performParam: .regularization, .normalization
          plotFcns: {'plotperform', plottrainstate, ploterrhist,
                    plotconfusion, plotroc}
        plotParams: {1x5 cell array of 5 params}
          trainFcn: 'trainscg'
        trainParam: .showWindow, .showCommandLine, .show, .epochs,
                    .time, .goal, .min_grad, .max_fail, .sigma,
                    .lambda

    weight and bias values:

                IW: {2x1 cell} containing 1 input weight matrix
                LW: {2x2 cell} containing 1 layer weight matrix
                 b: {2x1 cell} containing 2 bias vectors

My intention is not to create the exact net data structure, I would like to mainly implement the activation functions to different layers of my network as it is listed in above. Lets assume I can initialize the wights (network parameters).

I followed this post Getting Started with Deep Learning and Python as well as Multi-layer Perceptron to start. In the latter link, I learned that I can implement MLP by utilizing MLPclassifier from sklearn.neural_network library:

MLPClassifier(activation='relu', alpha=1e-05, batch_size='auto',
       beta_1=0.9, beta_2=0.999, early_stopping=False,
       epsilon=1e-08, hidden_layer_sizes=(5, 2), learning_rate='constant',
       learning_rate_init=0.001, max_iter=200, momentum=0.9,
       nesterovs_momentum=True, power_t=0.5, random_state=1, shuffle=True,
       solver='lbfgs', tol=0.0001, validation_fraction=0.1, verbose=False,
       warm_start=False)

However its setting is not exactly the one that I am trying to have. Reading MLPclassifier document page did not help me further.

I would appreciate if I get to know how-to implement such? I would be happy to be directed to any post or link which has already discussed this matter.

Thanks, Payam

$\endgroup$
0
$\begingroup$

Consider reusing an existing framework and adding the missing activation functions. For example, here you can see how to do that in sklearn.

However, notice that there might be other differences (consider this example) in how the algorithm is implemented, as with the rise of deep learning and convolution networks, neural networks have hugely grown in variety and complexity.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.