Tashkent university of information technologies named after muhammad al-khorezmi

import numpy as np
# Define the perceptron function
def perceptron(inputs, weights, bias):
# Calculate the weighted sum of inputs
weighted_sum = np.dot(inputs, weights) + bias
# Apply the step activation function
if weighted_sum > 0:
output = 1
else:
output = 0
return output
# Define the inputs, weights, and bias for the AND operation
inputs = np.array([1, 1]) # Input values
weights = np.array([0.5, 0.5]) # Weight values
bias = -1 # Bias value
# Perform the calculation using the perceptron
output = perceptron(inputs, weights, bias)
# Print the output
print("Output:", output)


Result:





In this example, we have defined the perceptron function that takes the inputs, weights, and bias as parameters. It calculates the weighted sum of the inputs, applies the step activation function, and returns the output.


We then define the inputs as an array of [1, 1], weights as [0.5, 0.5], and bias as -1, which represents the logical AND operation. Finally, we call the perceptron function with the inputs, weights, and bias, and print the output.


You can modify the inputs, weights, and bias to perform different calculations or implement other logical operations such as OR or XOR.