What fundamental component is at the core of neural networks?

The fundamental component of neural networks is the neuron (artificial neuron) — a computational element that takes several input signals, applies weights to them, sums them up, adds a bias, and passes the result through an activation function.

Main parts of a neuron:

• Inputs with weights
• Summator: calculates the weighted sum of inputs
• Activation function: a nonlinear function, such as ReLU, sigmoid, or tanh

Example of a simple neuron in Python:

import numpy as np

def neuron(inputs, weights, bias):
    total = np.dot(inputs, weights) + bias
    output = 1 / (1 + np.exp(-total))  # sigmoid
    return output

inputs = np.array([0.5, 0.3])
weights = np.array([0.9, -0.7])
bias = 0.1
print(neuron(inputs, weights, bias))

Thus, a neuron is a basic building block from which layers and the entire neural network are constructed.