Problema
A multi-class classifier outputs one probability per class (for example from softmax). Categorical cross-entropy punishes it for giving the correct class a low probability:
loss = -(ln(p₁) + ln(p₂) + … + ln(pₙ)) / n
where pᵢ is the probability the model gave to the correct class of sample i. To avoid ln(0), first raise any probability below 0.0000001 to 0.0000001.
Implement categorical_cross_entropy(probabilities, labels).
Input
probabilities: One row per sample, with one probability per class.
labels: The index of the correct class for each sample (0-based).
Output
Return the average loss as a decimal number.
Restrições
1 ≤ samples ≤ 1,000, 2 ≤ classes ≤ 100
0 ≤ each probability ≤ 1
0 ≤ labels[i] < number of classes
Exemplos
Entrada:
probabilities = [
[0.7, 0.2, 0.1],
[0.1, 0.8, 0.1]
]
labels = [0, 1]
Saída esperada:
expected = 0.289909
Entrada:
std::vector<std::vector<double>> probabilities = {
{0.7, 0.2, 0.1},
{0.1, 0.8, 0.1}
};
std::vector<long long> labels = {0, 1};
Saída esperada:
double expected = 0.289909;
Entrada:
double[][] probabilities = new double[][] {
new double[] {0.7, 0.2, 0.1},
new double[] {0.1, 0.8, 0.1}
};
long[] labels = new long[] {0, 1};
Saída esperada:
double expected = 0.289909;
Explicação
The correct classes got 0.7 and 0.8: -(ln(0.7) + ln(0.8)) / 2 = -(-0.356675 - 0.223144) / 2 ≈ 0.289909.
Entrada:
probabilities = [
[1.0, 0.0]
]
labels = [1]
Saída esperada:
expected = 16.118096
Entrada:
std::vector<std::vector<double>> probabilities = {
{1.0, 0.0}
};
std::vector<long long> labels = {1};
Saída esperada:
double expected = 16.118096;
Entrada:
double[][] probabilities = new double[][] {
new double[] {1.0, 0.0}
};
long[] labels = new long[] {1};
Saída esperada:
double expected = 16.118096;
Explicação
The correct class got probability 0, which is raised to 0.0000001, so the loss is -ln(0.0000001) ≈ 16.118096: a confident wrong answer is punished hard.
Como abordar
Tente sozinho primeiro e depois abra uma dica de cada vez.
Dica 1
Look up the probability assigned to each sample’s correct class, then average the negative logs of those values.
Dica 2
Clamp very small probabilities upward before taking logs to avoid undefined results.
Dica 3
Only the labeled class matters for each row, so ignore the other class probabilities when computing the loss.
Complexidade esperada
O(samples) time, O(1) extra space
Referências
Este desafio foi adaptado para o CodeUtility. Siga o enunciado e as restrições acima.