Single Artificial Neuron

An artificial neuron multiplies each input by a weight, adds a bias, and passes the result through an activation function:

z = x₁×w₁ + x₂×w₂ + … + xₙ×wₙ + bias

output = sigmoid(z) = 1 / (1 + e^(-z))

Implement neuron_output(inputs, weights, bias).

Input

inputs: The input values.

weights: One weight per input (same length as inputs).

bias: The neuron's bias.

Output

Return the neuron's output, a decimal number between 0 and 1.

Contraintes

1 ≤ length of inputs = length of weights ≤ 100

-10 ≤ each input, weight and bias ≤ 10

Exemples

Entrée :
bias = 0.5
inputs = [1.0, 2.0, 3.0]
weights = [0.2, 0.4, 0.6]

Sortie attendue :
expected = 0.964429

Entrée :
double bias = 0.5;
std::vector<double> inputs = {1.0, 2.0, 3.0};
std::vector<double> weights = {0.2, 0.4, 0.6};

Sortie attendue :
double expected = 0.964429;

Entrée :
double bias = 0.5;
double[] inputs = new double[] {1.0, 2.0, 3.0};
double[] weights = new double[] {0.2, 0.4, 0.6};

Sortie attendue :
double expected = 0.964429;

Entrée :
bias = 0.0
inputs = [0.5, -1.0]
weights = [2.0, 1.0]

Sortie attendue :
expected = 0.5

Entrée :
double bias = 0.0;
std::vector<double> inputs = {0.5, -1.0};
std::vector<double> weights = {2.0, 1.0};

Sortie attendue :
double expected = 0.5;

Entrée :
double bias = 0.0;
double[] inputs = new double[] {0.5, -1.0};
double[] weights = new double[] {2.0, 1.0};

Sortie attendue :
double expected = 0.5;

Références

Ce défi a été adapté pour CodeUtility. Suivez l'énoncé et les contraintes ci-dessus.

• Michael Nielsen, Neural Networks and Deep Learning
• Stanford CS231n, Neural Networks Part 1