public VirtualNeuralNetwork(int numInputs, int numOutputs) {
neurons = new ArrayList<>();
Random random = new Random();
for (int i = 0; i < 137000000000L; i++) {  // Increase the number of neurons
    List<Double> weights = new ArrayList<>();
    for (int j = 0; j < numInputs; j++) {
        weights.add(random.nextDouble());
    }
    double bias = random.nextDouble();
    neurons.add(new VirtualNeuron(bias, weights));
}

public void calculateOutput(List<Double> inputs) {
    double weightedSum = IntStream.range(0, inputs.size())
            .mapToDouble(i -> weights.get(i) * inputs.get(i))
            .sum();
    output = 1 / (1 + Math.exp(-weightedSum - bias));
}

public double getOutput() {
    return output;
}

// Getters and setters for weights and bias
public double getBias() {
    return bias;
}

public void setBias(double bias) {
    this.bias = bias;
}

public List<Double> getWeights() {
    return weights;
}

public void setWeights(List<Double> weights) {
    this.weights = weights;
}

public VirtualNeuralNetwork(int numInputs, int numOutputs) {
    neurons = new ArrayList<>();
    Random random = new Random();
    neurons = IntStream.range(0, numOutputs)
            .mapToObj(i -> new VirtualNeuron(random.nextDouble(),
                    random.doubles(numInputs).boxed().collect(Collectors.toList())))
            .collect(Collectors.toList());
}

public void processInput(List<Double> inputs) {
    neurons.forEach(neuron -> neuron.calculateOutput(inputs));
}

public List<Double> getOutputs() {
    return neurons.stream().map(VirtualNeuron::getOutput).collect(Collectors.toList());
}

// Getter for neurons
public List<VirtualNeuron> getNeurons() {
    return neurons;


}