Binary Cross-Entropy Loss
~12 mincode completion
Implement binary_cross_entropy(y_true, y_pred) that returns the mean BCE loss over the batch.
Examples
Mixed correct predictions
- Input
- binary_cross_entropy([1, 0, 1], [0.9, 0.1, 0.8])
- Output
- 0.14462
High-confidence correct predictions: low loss
- Input
- binary_cross_entropy([1, 1, 1], [0.9, 0.9, 0.9])
- Output
- 0.10536
Completely wrong predictions: high loss
- Input
- binary_cross_entropy([1, 0], [0.1, 0.9])
- Output
- 2.30259
Hints
Hint 1
bounds an array in one call.
Hint 2
Do not forget to clip causing log zero. That step is easy to skip.
Requirements
y_true: Ground-truth labels, 0 or 1, shape (m,)y_pred: Predicted probabilities in [0, 1], shape (m,)Return Scalar mean BCE loss.
Constraints
Allowed library: NumPy only
Time limit: 200 ms, Memory: 64 MB
Where this shows up
~12 min
••••••••••••••••
8 employers weight this skill
3 frontier labs, 2 big tech firms, 2 autonomy companies, 1 enterprise vendor. Top match scores 68.
Python
import numpy as np
def binary_cross_entropy(y_true: np.ndarray, y_pred: np.ndarray) -> float:
"""
Compute mean binary cross-entropy loss.
Args:
y_true: Ground-truth labels, 0 or 1, shape (m,)
y_pred: Predicted probabilities in [0, 1], shape (m,)
Returns:
Scalar mean BCE loss.
"""
# YOUR CODE HERE
pass