Neural Network BasicsMedium
Dense Layer Forward Pass
~18 mincode completion
Implement dense_forward(X, W, b) that returns .
Examples
Negative pre-activation clipped to 0
- Input
- dense_forward([[1, 2]], [[1, -1], [2, -2]], [0, 0])
- Output
- [[5, 0]]
Identity-like weights with bias
- Input
- dense_forward([[1, 0], [0, 1]], [[1], [1]], [0])
- Output
- [[1], [1]]
Hints
Hint 1
compares elementwise against a scalar or another array.
Hint 2
Do not forget to relu. That step is easy to skip.
Requirements
X: Input matrix of shape (m, n_in): Weight matrix of shape (n_in, n_out)
b: Bias vector of shape (n_out,)Return Output matrix of shape (m, n_out) after ReLU.
Constraints
Allowed library: NumPy only
Time limit: 200 ms, Memory: 64 MB
Where this shows up
~18 min
••••••••••••••••
8 employers weight this skill
4 frontier labs, 2 big tech firms, 1 autonomy company, 1 enterprise vendor. Top match scores 92.
Python
import numpy as np
def dense_forward(X: np.ndarray, W: np.ndarray, b: np.ndarray) -> np.ndarray:
"""
Compute the forward pass of a dense (ReLU) layer.
Args:
X: Input matrix of shape (m, n_in)
W: Weight matrix of shape (n_in, n_out)
b: Bias vector of shape (n_out,)
Returns:
Output matrix of shape (m, n_out) after ReLU.
"""
# YOUR CODE HERE
pass