#0017

ReLU Forward Pass

EasyML10 min10 XP

Problem

Given a NumPy array x, return ReLU(x), where negative values become 0 and positive values stay unchanged.

Why This Matters

ReLU is the tiny operation hiding inside many deep networks. Understanding it makes activation functions feel less mysterious.

Function Signature

def relu(x):

Examples

Example 1

Inputx = np.array([-2, 0, 3, -1, 5])

Outputarray([0, 0, 3, 0, 5])

Negative numbers are clipped to 0. Non-negative numbers pass through.

Constraints

Input may be a scalar, vector, or matrix.
Return a NumPy array or scalar with the same shape.
Do not use Python loops for array inputs.

CodePython

import numpy as np

def relu(x):
    """
    Input example: x = np.array([-2, 0, 3, -1, 5])
    Return: array([0, 0, 3, 0, 5])
    Return the value from the function so the tests can compare it. Do not print unless the prompt asks.
    """
    # write your code here
    return x

import numpy as np

def relu(x):
    """
    Input example: x = np.array([-2, 0, 3, -1, 5])
    Return: array([0, 0, 3, 0, 5])
    Return the value from the function so the tests can compare it. Do not print unless the prompt asks.
    """
    # write your code here
    return x

Visible browser tests run here when available.

Testcases2 visible / 4 hidden categories

Vector with mixed signs

Input[-2, 0, 3, -1, 5]

Expected[0, 0, 3, 0, 5]

ReLU keeps positive signal and removes negative signal.

Matrix input

Input[[-1, 2], [3, -4]]

Expected[[0, 2], [3, 0]]

The same rule is applied independently to every cell.

Hidden Test Categories

All negative valuesAll positive valuesFloating point valuesScalar input