Bio vs Artificial neuron

Understanding the fundamental difference between biological neurons (inspired by the brain) and artificial neurons (used in deep learning) is crucial to grasp how neural networks operate.

A biological neuron is a cell in the human nervous system that transmits information through electrical and chemical signals. In contrast, an artificial neuron is a mathematical model designed to mimic the behavior of its biological counterpart but in a simplified manner.

Here's how they compare:

• Biological Neuron: Receives input via dendrites, processes it in the soma, and sends output through the axon.
• Artificial Neuron: Receives input values, applies weights, sums them, passes the result through an activation function, and outputs a value.

A diagram of a biological neuron

An abstract representation of an artificial neuron

This example demonstrates how an artificial neuron processes input using weights, bias, and an activation function:

import numpy as np

# Sigmoid activation function
def sigmoid(x):
    return 1 / (1 + np.exp(-x))

# Artificial neuron computation
def artificial_neuron(inputs, weights, bias):
    weighted_sum = np.dot(inputs, weights) + bias
    return sigmoid(weighted_sum)

# Example inputs
inputs = np.array([0.7, 0.3])
weights = np.array([0.6, 0.4])
bias = 0.1

output = artificial_neuron(inputs, weights, bias)
print("Neuron Output:", output)

This code performs the following:

• Computes a weighted sum of the input features
• Adds a bias term
• Applies a sigmoid activation function