我希望这里有人能帮我:
我试图实现一个神经网络来寻找数据簇,这是一个二维的簇我试图遵循wikipedia中描述的标准算法:我为每个数据点寻找最小距离,并向数据点更新该神经元的权重。当总距离足够小时,我就停止这样做。
我的结果是找到了大多数的星团,但是在一个视图上是错误的,虽然它计算了一个永久距离,但它不再会聚。我的错误在哪里?

typedef struct{
    double x;
    double y;
}Data;

typedef struct{
    double x;
    double y;
}Neuron;

typedef struct{
    size_t numNeurons;
    Neuron* neurons;
}Network;

int main(void){
    srand(time(NULL));

    Data trainingData[1000];
    size_t sizeTrainingData = 0;
    size_t sizeClasses = 0;
    Network network;

    getData(trainingData, &sizeTrainingData, &sizeClasses);

    initializeNetwork(&network, sizeClasses);
    normalizeData(trainingData, sizeTrainingData);
    train(&network, trainingData, sizeTrainingData);

    return 0;
}

void train(Network* network, Data trainingData[], size_t sizeTrainingData){
    for(int epoch=0; epoch<TRAINING_EPOCHS; ++epoch){
        double learningRate = getLearningRate(epoch);
        double totalDistance = 0;
        for(int i=0; i<sizeTrainingData; ++i){
            Data currentData = trainingData[i];
            int winningNeuron = 0;
            totalDistance += findWinningNeuron(network, currentData, &winningNeuron);
            //update weight
            network->neurons[i].x += learningRate * (currentData.x - network->neurons[i].x);
            network->neurons[i].y += learningRate * (currentData.y - network->neurons[i].y);
        }
        if(totalDistance<MIN_TOTAL_DISTANCE) break;
    }
}

double getLearningRate(int epoch){
    return LEARNING_RATE * exp(-log(LEARNING_RATE/LEARNING_RATE_MIN_VALUE)*((double)epoch/TRAINING_EPOCHS));
}

double findWinningNeuron(Network* network, Data data, int* winningNeuron){
    double smallestDistance = 9999;
    for(unsigned int currentNeuronIndex=0; currentNeuronIndex<network->numNeurons; ++currentNeuronIndex){
        Neuron neuron = network->neurons[currentNeuronIndex];
        double distance = sqrt(pow(data.x-neuron.x,2)+pow(data.y-neuron.y,2));
        if(distance<smallestDistance){
            smallestDistance = distance;
            *winningNeuron = currentNeuronIndex;
        }
    }
    return smallestDistance;
}

initializeNetwork(...)以-1和1范围内的随机权重启动所有神经元。
normalizeData(...)以某种方式规格化,因此最大值为1。
例如:
如果我给网络提供大约50个(标准化的)数据点,这些数据点分成3个簇,那么剩下的totaldistance保持在大约7.3。当我检查神经元的位置时,它应该代表了簇的中心,两个是完美的,一个在簇的边缘。不是应该用算法把它移到中心吗?我重复了好几次算法,结果总是相似的(在完全相同的错误点上)

最佳答案

你的代码看起来不像LVQ,特别是你从来没有使用过获胜的神经元,而你应该只移动这个

void train(Network* network, Data trainingData[], size_t sizeTrainingData){
    for(int epoch=0; epoch<TRAINING_EPOCHS; ++epoch){
        double learningRate = getLearningRate(epoch);
        double totalDistance = 0;
        for(int i=0; i<sizeTrainingData; ++i){
            Data currentData = trainingData[i];
            int winningNeuron = 0;
            totalDistance += findWinningNeuron(network, currentData, &winningNeuron);
            //update weight
            network->neurons[i].x += learningRate * (currentData.x - network->neurons[i].x);
            network->neurons[i].y += learningRate * (currentData.y - network->neurons[i].y);
        }
        if(totalDistance<MIN_TOTAL_DISTANCE) break;
    }
}

你要移动的神经元在winningNeuron中,但是你更新了第i个神经元,在那里i实际上在训练样本上重复,我很惊讶你没有从你的记忆中掉下来(网络->神经元应该小于SizeTrainingData)。我想你的意思是
void train(Network* network, Data trainingData[], size_t sizeTrainingData){
    for(int epoch=0; epoch<TRAINING_EPOCHS; ++epoch){
        double learningRate = getLearningRate(epoch);
        double totalDistance = 0;
        for(int i=0; i<sizeTrainingData; ++i){
            Data currentData = trainingData[i];
            int winningNeuron = 0;
            totalDistance += findWinningNeuron(network, currentData, &winningNeuron);
            //update weight
            network->neurons[winningNeuron].x += learningRate * (currentData.x - network->neurons[winningNeuron].x);
            network->neurons[winningNeuron].y += learningRate * (currentData.y - network->neurons[winningNeuron].y);
        }
        if(totalDistance<MIN_TOTAL_DISTANCE) break;
    }
}

关于c - ANN:学习 vector 量化无效,我们在Stack Overflow上找到一个类似的问题:https://stackoverflow.com/questions/34415829/

10-09 17:52