Synapses

Neuron Firing

The input to a Neuron

So how about artificial neural networks

Activation Function

Sigmoid Function

Step Function

Learning

A foreword on learning

Learning in perceptrons

The Learning Rule

Training

So what can we use do with neural networks

Single layer neural networks

Multi layer neural networks

Perceptron Configuration ( Single layer network)

So Now The New Stuff (More layers)

What Does The New Network Look Like

Types Of Learning

Reinforcement

Learning Algorithm

1. নিউরাল নেটওয়ার্কে এলোমেলো ওজন (এবং পক্ষপাত) দিয়ে শুরু করুন 
2. প্রশিক্ষণ সংস্থার এক বা একাধিক সদস্যকে চেষ্টা করুন, আউটপুট (গুলি) কী হতে হবে তার সাথে তুলনা করে দেখুন (লক্ষ্য আউটপুট (গুলি) এর তুলনায়) 
3. জিগল ওজন কিছুটা, 
4. আউটপুটগুলিতে উন্নতি পাওয়ার লক্ষ্য এখন প্রশিক্ষণের নতুন একটি সেট নিয়ে চেষ্টা করুন, বা আবার পুনরাবৃত্তি করুন, 
5. ঝাঁকুনি প্রতিটি সময় আপনি বেশ নির্ভুল ফলাফল খুঁজে না পাওয়া পর্যন্ত পুনরাবৃত্তি করুন

Things To Watch Out For

Part 3

Summary

Part 1: Perceptron Configuration (Single Layer Network)

Part 2: Multi-Layer Configuration

Learning

Reinforcement

Supervised

So Now the New Stuff

So How Does This Translate Into an Algorithm

• Pick two genotypes at random
• Compare scores (fitness) to come up with a winner and loser
• Go along genotype, at each locus (point)
  So only the loser gets changed, which gives a version of Elitism for free; this ensures the best in breed remains in the population.
  • With some probability, copy from winner to loser (overwrite)
  • With some probability, mutate that locus of the loser

1. The genotype will be different for a different problem domain
2. The fitness function will be different for a different problem domain

1. The Geneotype

//ANN's
private NeuralNetwork[] networks;

public GA_Trainer_XOR()
{
    networks = new NeuralNetwork[POPULATION];
    //create new ANN objects, random weights applied at start
    for (int i = 0; i <= networks.GetUpperBound(0); i++)
    {
       networks[i] = new NeuralNetwork(2, 2, 1);
       networks[i].Change += 
         new NeuralNetwork.ChangeHandler(GA_Trainer_NN_Change);
    }
}

2. The Fitness Function

public double getError(double[] targets)
{
    //storage for error
    double error = 0.0;
    //this calculation is based on something I read about weight space in
    //Artificial Intellegence - A Modern Approach, 2nd edition.Prentice Hall
    //2003. Stuart Rusell, Peter Norvig. Pg 741
    error = Math.Sqrt(Math.Pow((targets[0] - outputs[0]), 2));
    return error;
}

private double evaluate(int popMember)
{
    double error = 0.0;
    //loop through the entire training set
    for (int i = 0; i <= train_set.GetUpperBound(0); i++)
    {
        //forward these new values through network
        //forward weights through ANN
        forwardWeights(popMember, getTrainSet(i));
        double[] targetValues = getTargetValues(getTrainSet(i));
        error += networks[popMember].getError(targetValues);
    }
    //if the Error term is < acceptableNNError value we have found
    //a good configuration of weights for teh NeuralNetwork, so tell
    //GA to stop looking
    if (error < acceptableNNError)
    {
        bestConfiguration = popMember;
        foundGoodANN = true;
    }
    //return error
    return error;
}

//check to see if there was a best configuration found, may not have done
//enough training to find a good NeuralNetwork configuration, so will simply
//have to return the WINNER
if (bestConfiguration == -1)
{
    bestConfiguration = WINNER;
}
//return the best Neural network
return networks[bestConfiguration];

So Finally the Code

• GA_Trainer_XOR: Trains a neural network to solve the XOR problem using a Microbial GA.
• TrainerEventArgs: Training event args, for use with a GUI.
• NeuralNetwork: A configurable neural network.
• NeuralNetworkEventArgs: Training event args, for use with a GUI.
• SigmoidActivationFunction: A static method to provide the sigmoid activation function.

Code Demos

Live Results Tab

• Sudoko solver (the popular game)
• Backpack problem (trying to optimize the use of a backpack of limited size, to get as many items in as will fit)
• Favourite pizza toppings problem (try and find out what someone's favourite pizza is)

Training Results Tab

Trained Results Tab

What Do You Think?

Points of Interest

History

• v1.1: 27/12/06: Modified the GA_Trainer_XOR class to have a random number seed of 5.
• v1.0: 11/12/06: Initial article.

Bibliography

• Artificial Intelligence 2nd edition, Elaine Rich / Kevin Knight. McGraw Hill Inc.
• Artificial Intelligence, A Modern Approach, Stuart Russell / Peter Norvig. Prentice Hall.