Neuron — the linear score z = wᵀx + b

Background

Every neuron starts the same way: an affine map of the inputs.

$$z = \mathbf{w}^\top \mathbf{x} + b$$

This single number $z$ is the neuron's pre-activation score. Linear regression, logistic regression, and the perceptron all compute this same $z$ — they differ only in what they do after it. Getting $z$ right is the foundation of the whole course.

Problem statement

Implement neuron_score(x, w, b) returning the scalar $\mathbf{w}^\top\mathbf{x} + b$ for one input.

Input

• x — array-like feature vector of length $n$.
• w — array-like weight vector of length $n$.
• b — float, the bias.

Output

Returns a Python float: the linear score $z$.

Examples

Example 1

Input:  x = [2, 3], w = [2, 3], b = -5
Output: 8.0

Explanation: $2\cdot2 + 3\cdot3 - 5 = 4 + 9 - 5 = 8$.

Example 2 — bias shifts the score

Input:  x = [0, 0], w = [1, 1], b = 0.7
Output: 0.7

Explanation: with zero inputs only the bias survives, which is exactly why $b$ lets the boundary avoid the origin.

Constraints

• Compute the dot product $\mathbf{w}^\top\mathbf{x}$ and add b.
• Return a plain float.

Notes

• The bias $b$ shifts $z$ up or down independently of the inputs — that is what lets a neuron's decision boundary sit anywhere, not just through the origin.