Neural network output in c++

Question

I want to create a function that calculates neural network output. The elements of my NN is a 19D input vector and a 19D output vector. I choose one hidden layer with 50 neurons. My code is the following but i am not quite sure if it works properly.

double *BuildPlanner::neural_tactics(){


    norm();  //normalize input vector
    ReadFromFile();   // load weights W1 W2 b1

    double hiddenLayer [50][1];


    for(int h=0; h<50; h++){
            hiddenLayer[h][0] =0;
            for(int f = 0; f < 19; f++){

                    hiddenLayer[h][0] = hiddenLayer[h][0] + W1[h][f]*input1[f][0];
            }
    }

    double HiddenLayer[50][1];

    for(int h=0; h<50; h++){
            HiddenLayer[h][0] = tanh(hiddenLayer[h][0] + b1[h][0]);
    }

    double outputLayer[50][1];

    for(int h=0; h<19; h++){
            for(int k=0; k<50; k++){
                    outputLayer[h][0] = outputLayer[h][0] + W2[h][k]*HiddenLayer[k][0];
            }
    }

    double Output[19];

    for(int h=0; h<19; h++){

            Output[h] = tanh(outputLayer[h][0]);
    }

    return Output;
}

Actually I not quite sure about the matrices multiplication. W1*input+b1 where the size of the matrices are 50x19 * 19x1 + 50x1 and W2*outHiddenLayer 19x50*50x1!

You could start by not hardcoding all those sizes, so you can easily plug in some small numbers and go through the result by hand. — Thomas
– Thomas, Commented Sep 4, 2012 at 17:49
Yea its a good start. But actually my problem is if multiplications works as the way i want! — Jose Ramon
– Jose Ramon, Commented Sep 4, 2012 at 17:57
Check this library: sourceforge.net/projects/c-c-neural-networks — SomethingSomething
– SomethingSomething, Commented Aug 15, 2015 at 12:26

Matt Phillips · Accepted Answer · 2012-09-04 18:15:43Z

1

Your matrix multiplication looks ok to me, but there are other problems--`outputLayer is 50x1 but a) you only iterate through the first 19 elements, and b) you have it on the RHS of your equation

outputLayer[h][0] = outputLayer[h][0] + W2[h][k]...

before that element has ever been defined. That could be causing all your problems. Also, although I assume you're making outputLayer 2-dimensional to make them look matrix-like, it's completely gratuitous and slows things down when the second dimension has size 1--just declare it and the others as

double outputLayer[50];

since it's a vector and those are always one dimensional so it will actually make your code clearer.

answered Sep 4, 2012 at 18:15

Matt Phillips

9,7918 gold badges48 silver badges77 bronze badges

Sign up to request clarification or add additional context in comments.

2 Comments

Jose Ramon Over a year ago

outputLayer the output of NN has 19x1 size. Wrong definition! Just forgot to change 50 to 19!!

Matt Phillips Over a year ago

@FereRes Ok. But of course b) is really the main problem and would explain why your results are 'weird'--using undefined values won't in this case create compile- or run-time errors, but just lead to undefined behavior.

Collectives™ on Stack Overflow

Neural network output in c++

1 Answer 1

2 Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

2 Comments

Your Answer

Sign up or log in

Post as a guest

Related