Batch Normalization Forward
~15 mincode completion
Implement batch_normalize(X, eps) that normalizes each feature column.
Examples
Each column has unit std (check element value)
- Input
- batch_normalize([[1, 2], [3, 4], [5, 6]], 0)
- Output
- [[-1.22474, -1.22474], [0, 0], [1.22474, 1.22474]]
Hints
Hint 1
The reduction runs down the columns, so pass .
Hint 2
Watch for this: normalized along wrong axis.
Requirements
X: Input matrix of shape (m, d)eps: Small constant for numerical stabilityReturn Normalized matrix of shape (m, d).
Constraints
Allowed library: NumPy only
Time limit: 200 ms, Memory: 64 MB
Try similar problems(1)
Where this shows up
~15 min
••••••••••••••••
8 employers weight this skill
4 frontier labs, 2 big tech firms, 1 autonomy company, 1 enterprise vendor. Top match scores 78.
Python
import numpy as np
def batch_normalize(X: np.ndarray, eps: float = 1e-8) -> np.ndarray:
"""
Normalize each feature (column) of X to zero mean and unit variance.
Args:
X: Input matrix of shape (m, d)
eps: Small constant for numerical stability
Returns:
Normalized matrix of shape (m, d).
"""
# YOUR CODE HERE
pass