Logo Questions Linux Laravel Mysql Ubuntu Git Menu
 

Using Neural Network to solve Y = X * X + b type formula

Update 1/6/2014: I've updated the question so that I'm trying to solve a non-linear equation. As many of you pointed out I didn't need the extra complexity (hidden-layer, sigmoid function, etc) in order to solve a non-linear problem.

Also, I realize I could probably solve even non-linear problems like this using other means besides neural networks. I'm not trying to write the most efficient code or the least amount of code. This is purely for me to better learn neural networks.


I've created my own implementation of back propagated neural network.

It is working fine when trained to solve simple XOR operations.

However now I want to adapt it & train it to solve Y = X * X + B type formulas, but I'm not getting expected results. After training the network does not calculate the correct answers. Are neural networks well-suited for solving algebra equations like this? I realize my example is trivial I'm just trying to learn more about neural networks and their capabilities.

My hidden layer is using a sigmoid activation function and my output layer is using an identity function.

If you could analyze my code and point out any errors I'd be grateful.

Here is my full code (C# .NET):

using System;
using System.Collections.Generic;
using System.Linq;
using System.Text;

namespace NeuralNetwork
{
    class Program
    {
        static void Main(string[] args)
        {
            Console.WriteLine("Training Network...");

            Random r = new Random();
            var network = new NeuralNetwork(1, 5, 1);
            for (int i = 0; i < 100000; i++)
            {
                int x = i % 15;
                int y = x * x + 10;
                network.Train(x);
                network.BackPropagate(y);
            }

            //Below should output 20, but instead outputs garbage
            Console.WriteLine("0 * 0 + 10 = " + network.Compute(0)[0]);

            //Below should output 110, but instead outputs garbage
            Console.WriteLine("10 * 10 + 10 = " + network.Compute(10)[0]);

            //Below should output 410, but instead outputs garbage
            Console.WriteLine("20 * 20 + 10 = " + network.Compute(20)[0]);
        }
    }

    public class NeuralNetwork
    {
        public double LearnRate { get; set; }
        public double Momentum { get; set; }
        public List<Neuron> InputLayer { get; set; }
        public List<Neuron> HiddenLayer { get; set; }
        public List<Neuron> OutputLayer { get; set; }
        static Random random = new Random();

        public NeuralNetwork(int inputSize, int hiddenSize, int outputSize)
        {
            LearnRate = .9;
            Momentum = .04;
            InputLayer = new List<Neuron>();
            HiddenLayer = new List<Neuron>();
            OutputLayer = new List<Neuron>();

            for (int i = 0; i < inputSize; i++)
                InputLayer.Add(new Neuron());

            for (int i = 0; i < hiddenSize; i++)
                HiddenLayer.Add(new Neuron(InputLayer));

            for (int i = 0; i < outputSize; i++)
                OutputLayer.Add(new Neuron(HiddenLayer));
        }

        public void Train(params double[] inputs)
        {
            int i = 0;
            InputLayer.ForEach(a => a.Value = inputs[i++]);
            HiddenLayer.ForEach(a => a.CalculateValue());
            OutputLayer.ForEach(a => a.CalculateValue());
        }

        public double[] Compute(params double[] inputs)
        {
            Train(inputs);
            return OutputLayer.Select(a => a.Value).ToArray();
        }

        public double CalculateError(params double[] targets)
        {
            int i = 0;
            return OutputLayer.Sum(a => Math.Abs(a.CalculateError(targets[i++])));
        }

        public void BackPropagate(params double[] targets)
        {
            int i = 0;
            OutputLayer.ForEach(a => a.CalculateGradient(targets[i++]));
            HiddenLayer.ForEach(a => a.CalculateGradient());
            HiddenLayer.ForEach(a => a.UpdateWeights(LearnRate, Momentum));
            OutputLayer.ForEach(a => a.UpdateWeights(LearnRate, Momentum));
        }

        public static double NextRandom()
        {
            return 2 * random.NextDouble() - 1;
        }

        public static double SigmoidFunction(double x)
        {
            if (x < -45.0) return 0.0;
            else if (x > 45.0) return 1.0;
            return 1.0 / (1.0 + Math.Exp(-x));
        }

        public static double SigmoidDerivative(double f)
        {
            return f * (1 - f);
        }

        public static double HyperTanFunction(double x)
        {
            if (x < -10.0) return -1.0;
            else if (x > 10.0) return 1.0;
            else return Math.Tanh(x);
        }

        public static double HyperTanDerivative(double f)
        {
            return (1 - f) * (1 + f);
        }

        public static double IdentityFunction(double x)
        {
            return x;
        }

        public static double IdentityDerivative()
        {
            return 1;
        }
    }

    public class Neuron
    {
        public bool IsInput { get { return InputSynapses.Count == 0; } }
        public bool IsHidden { get { return InputSynapses.Count != 0 && OutputSynapses.Count != 0; } }
        public bool IsOutput { get { return OutputSynapses.Count == 0; } }
        public List<Synapse> InputSynapses { get; set; }
        public List<Synapse> OutputSynapses { get; set; }
        public double Bias { get; set; }
        public double BiasDelta { get; set; }
        public double Gradient { get; set; }
        public double Value { get; set; }

        public Neuron()
        {
            InputSynapses = new List<Synapse>();
            OutputSynapses = new List<Synapse>();
            Bias = NeuralNetwork.NextRandom();
        }

        public Neuron(List<Neuron> inputNeurons) : this()
        {
            foreach (var inputNeuron in inputNeurons)
            {
                var synapse = new Synapse(inputNeuron, this);
                inputNeuron.OutputSynapses.Add(synapse);
                InputSynapses.Add(synapse);
            }
        }

        public virtual double CalculateValue()
        {
            var d = InputSynapses.Sum(a => a.Weight * a.InputNeuron.Value) + Bias;
            return Value = IsHidden ? NeuralNetwork.SigmoidFunction(d) : NeuralNetwork.IdentityFunction(d);
        }

        public virtual double CalculateDerivative()
        {
            var d = Value;
            return IsHidden ? NeuralNetwork.SigmoidDerivative(d) : NeuralNetwork.IdentityDerivative();
        }

        public double CalculateError(double target)
        {
            return target - Value;
        }

        public double CalculateGradient(double target)
        {
            return Gradient = CalculateError(target) * CalculateDerivative();
        }

        public double CalculateGradient()
        {
            return Gradient = OutputSynapses.Sum(a => a.OutputNeuron.Gradient * a.Weight) * CalculateDerivative();
        }

        public void UpdateWeights(double learnRate, double momentum)
        {
            var prevDelta = BiasDelta;
            BiasDelta = learnRate * Gradient; // * 1
            Bias += BiasDelta + momentum * prevDelta;

            foreach (var s in InputSynapses)
            {
                prevDelta = s.WeightDelta;
                s.WeightDelta = learnRate * Gradient * s.InputNeuron.Value;
                s.Weight += s.WeightDelta + momentum * prevDelta;
            }
        }
    }

    public class Synapse
    {
        public Neuron InputNeuron { get; set; }
        public Neuron OutputNeuron { get; set; }
        public double Weight { get; set; }
        public double WeightDelta { get; set; }

        public Synapse(Neuron inputNeuron, Neuron outputNeuron)
        {
            InputNeuron = inputNeuron;
            OutputNeuron = outputNeuron;
            Weight = NeuralNetwork.NextRandom();
        }
    }
}
like image 327
craigrs84 Avatar asked Nov 01 '22 07:11

craigrs84


1 Answers

you use sigmoid as output funnction which in in the range [0-1] but you target value is double the range is [ 0 - MAX_INT ], i think it is the basic resaon why you are getting NAN。 i update you code , and try to normalize the value in the range in [0-1], and I can get ouptut like this which is what I expect

I think I am getting close to the truth,I am not sure why this answer is getting vote down enter image description here

using System;
using System.Collections.Generic;
using System.Linq;
using System.Text;

namespace NeuralNetwork
{
    class Program
    {
        static void Main(string[] args)
        {
            Console.WriteLine("Training Network...");

            Random r = new Random();
            var network = new NeuralNetwork(1, 3, 1);
            for (int k = 0; k < 60; k++)
            {
                for (int i = 0; i < 1000; i++)
                {
                    double x = i / 1000.0;// r.Next();
                    double y = 3 * x;
                    network.Train(x);
                    network.BackPropagate(y);
                }
                double output = network.Compute(0.2)[0];
                Console.WriteLine(output);
            }
            //Below should output 10, but instead outputs either a very large number or NaN
           /* double output = network.Compute(3)[0];
            Console.WriteLine(output);*/
        }
    }

    public class NeuralNetwork
    {
        public double LearnRate { get; set; }
        public double Momentum { get; set; }
        public List<Neuron> InputLayer { get; set; }
        public List<Neuron> HiddenLayer { get; set; }
        public List<Neuron> OutputLayer { get; set; }
        static Random random = new Random();

        public NeuralNetwork(int inputSize, int hiddenSize, int outputSize)
        {
            LearnRate = .2;
            Momentum = .04;
            InputLayer = new List<Neuron>();
            HiddenLayer = new List<Neuron>();
            OutputLayer = new List<Neuron>();

            for (int i = 0; i < inputSize; i++)
                InputLayer.Add(new Neuron());

            for (int i = 0; i < hiddenSize; i++)
                HiddenLayer.Add(new Neuron(InputLayer));

            for (int i = 0; i < outputSize; i++)
                OutputLayer.Add(new Neuron(HiddenLayer));
        }

        public void Train(params double[] inputs)
        {
            int i = 0;
            InputLayer.ForEach(a => a.Value = inputs[i++]);
            HiddenLayer.ForEach(a => a.CalculateValue());
            OutputLayer.ForEach(a => a.CalculateValue());
        }

        public double[] Compute(params double[] inputs)
        {
            Train(inputs);
            return OutputLayer.Select(a => a.Value).ToArray();
        }

        public double CalculateError(params double[] targets)
        {
            int i = 0;
            return OutputLayer.Sum(a => Math.Abs(a.CalculateError(targets[i++])));
        }

        public void BackPropagate(params double[] targets)
        {
            int i = 0;
            OutputLayer.ForEach(a => a.CalculateGradient(targets[i++]));
            HiddenLayer.ForEach(a => a.CalculateGradient());
            HiddenLayer.ForEach(a => a.UpdateWeights(LearnRate, Momentum));
            OutputLayer.ForEach(a => a.UpdateWeights(LearnRate, Momentum));
        }

        public static double NextRandom()
        {
            return 2 * random.NextDouble() - 1;
        }

        public static double SigmoidFunction(double x)
        {
           if (x < -45.0)
            {
                return 0.0;
            }
            else if (x > 45.0)
            {
                return 1.0;
            }
            return 1.0 / (1.0 + Math.Exp(-x));

        }

        public static double SigmoidDerivative(double f)
        {
            return f * (1 - f);
        }

        public static double HyperTanFunction(double x)
        {
            if (x < -10.0) return -1.0;
            else if (x > 10.0) return 1.0;
            else return Math.Tanh(x);
        }

        public static double HyperTanDerivative(double f)
        {
            return (1 - f) * (1 + f);
        }

        public static double IdentityFunction(double x)
        {
            return x;
        }

        public static double IdentityDerivative()
        {
            return 1;
        }
    }

    public class Neuron
    {
        public bool IsInput { get { return InputSynapses.Count == 0; } }
        public bool IsHidden { get { return InputSynapses.Count != 0 && OutputSynapses.Count != 0; } }
        public bool IsOutput { get { return OutputSynapses.Count == 0; } }
        public List<Synapse> InputSynapses { get; set; }
        public List<Synapse> OutputSynapses { get; set; }
        public double Bias { get; set; }
        public double BiasDelta { get; set; }
        public double Gradient { get; set; }
        public double Value { get; set; }

        public Neuron()
        {
            InputSynapses = new List<Synapse>();
            OutputSynapses = new List<Synapse>();
            Bias = NeuralNetwork.NextRandom();
        }

        public Neuron(List<Neuron> inputNeurons)
            : this()
        {
            foreach (var inputNeuron in inputNeurons)
            {
                var synapse = new Synapse(inputNeuron, this);
                inputNeuron.OutputSynapses.Add(synapse);
                InputSynapses.Add(synapse);
            }
        }

        public virtual double CalculateValue()
        {
            var d = InputSynapses.Sum(a => a.Weight * a.InputNeuron.Value);// + Bias;
            return Value = IsHidden ? NeuralNetwork.SigmoidFunction(d) : NeuralNetwork.IdentityFunction(d);
        }

        public virtual double CalculateDerivative()
        {
            var d = Value;
            return IsHidden ? NeuralNetwork.SigmoidDerivative(d) : NeuralNetwork.IdentityDerivative();
        }

        public double CalculateError(double target)
        {
            return target - Value;
        }

        public double CalculateGradient(double target)
        {
            return Gradient = CalculateError(target) * CalculateDerivative();
        }

        public double CalculateGradient()
        {
            return Gradient = OutputSynapses.Sum(a => a.OutputNeuron.Gradient * a.Weight) * CalculateDerivative();
        }

        public void UpdateWeights(double learnRate, double momentum)
        {
            var prevDelta = BiasDelta;
            BiasDelta = learnRate * Gradient; // * 1
            Bias += BiasDelta + momentum * prevDelta;

            foreach (var s in InputSynapses)
            {
                prevDelta = s.WeightDelta;
                s.WeightDelta = learnRate * Gradient * s.InputNeuron.Value;
                s.Weight += s.WeightDelta; //;+ momentum * prevDelta;
            }
        }
    }

    public class Synapse
    {
        public Neuron InputNeuron { get; set; }
        public Neuron OutputNeuron { get; set; }
        public double Weight { get; set; }
        public double WeightDelta { get; set; }

        public Synapse(Neuron inputNeuron, Neuron outputNeuron)
        {
            InputNeuron = inputNeuron;
            OutputNeuron = outputNeuron;
            Weight = NeuralNetwork.NextRandom();
        }
    }
}
like image 94
michaeltang Avatar answered Nov 15 '22 04:11

michaeltang