Getting NaN values in neural network weight matrices

I am trying to develop a feedforward NN in MATLAB. I have a dataset of 12 inputs and 1 output with 46998 samples. I have some NaN values in last rows of Matrix, because some inputs are accelerations & velocities which are 1 & 2 steps less respectively than displacements. With this current data set I am getting w1_grad & w2_grad as NaN matrices. I tried to remove them using

Heave_dataset(isnan(Heave_dataset))=[];

but my dataset is getting converted into a column matrix of (1*610964).

can anyone help me with this ?

clc;
clear all;
close all;
mkdir('Results//'); %Directory for Storing Results

%%Configurations/Parameters

load 'Heave_dataset'

% Heave_dataset(isnan(Heave_dataset))=[];

nbrOfNeuronsInEachHiddenLayer = 24; 
nbrOfOutUnits = 1;
unipolarBipolarSelector = -1; %0 for Unipolar, -1 for Bipolar
learningRate = 0.08;
nbrOfEpochs_max = 50000;

%%Read Data

Input = Heave_dataset(:, 1:length(Heave_dataset(1,:))-1);
TargetClasses = Heave_dataset(:, length(Heave_dataset(1,:)));

%%Calculate Number of Input and Output NodesActivations

nbrOfInputNodes = length(Input(1,:)); %=Dimention of Any Input Samples
nbrOfLayers = 2 + length(nbrOfNeuronsInEachHiddenLayer);
nbrOfNodesPerLayer = [nbrOfInputNodes nbrOfNeuronsInEachHiddenLayer nbrOfOutUnits];

%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%Forward Pass %%%%%%%%%%%

%%Adding the Bias to Input layer

Input = [ones(length(Input(:,1)),1) Input];

%%Weights leading from input layer to hidden layer is w1

w1 = rand(nbrOfNeuronsInEachHiddenLayer,(nbrOfInputNodes+1));

%%Input & output of hidde layer

hiddenlayer_input = Input*w1';

hiddenlayer_output = -1 + 2./(1 + exp(-(hiddenlayer_input)));

%%Adding the Bias to hidden layer

hiddenlayer_output = [ones(length(hiddenlayer_output(:,1)),1) hiddenlayer_output];

%%Weights leading from input layer to hidden layer is w1

w2 = rand(nbrOfOutUnits,(nbrOfNeuronsInEachHiddenLayer+1));

%%Input & output of hidde layer

outerlayer_input = hiddenlayer_output*w2';

outerlayer_output = outerlayer_input;

%%Error Calculation

TotalError = 0.5*(TargetClasses-outerlayer_output).^2;

%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%Backward Pass %%%%%%%%%%%

d3 = outerlayer_output - TargetClasses;

d2 = (d3*w2).*hiddenlayer_output.*(1-hiddenlayer_output);

d2 = d2(:,2:end);

D1 = d2' * Input;

D2 = d3' * hiddenlayer_output;

w1_grad = D1/46998 + learningRate*[zeros(size(w1,1),1) w1(:,2:end)]/46998;

w2_grad = D2/46998 + learningRate*[zeros(size(w2,1),1) w2(:,2:end)]/46998;

Answer 1

[Greg Heath]

Remove all input and corresponding output vectors if EITHER OR BOTH contain NaNs.

Hope this helps

Thank you for formally accepting my answer

Greg

[Tulasi Ram Tammu]

Thank You

Answer 2

[Teja Muppirala]

As of R2016b, you could use the RMMISSING function.

Heave_dataset = rmmissing(Heave_dataset);

Or you can do it like this.

Heave_dataset(any(isnan(Heave_dataset),2),:)=[];

You might want to make this two lines, just to be more readable.

missingRows = any(isnan(Heave_dataset),2);
Heave_dataset(missingRows,:) = [];

The way you have written now, it removes the NaN values, but not the rows, so it has to turn the matrix into a long vector of all the values.

[Tulasi Ram Tammu]

Thank You