22  Perceptron

import numpy as np

22.1 Step function (activation function)

# Step function (activation function)
def step_function(x):
    return 1 if x >= 0 else 0

22.2 Perceptron Model

# Perceptron model
class Perceptron:
    def __init__(self, input_size, learning_rate=0.1):
        self.weights = np.zeros(input_size + 1)  # Initialize weights and bias to 0
        self.learning_rate = learning_rate

    def predict(self, inputs):
        # Add bias term to the inputs
        summation = np.dot(inputs, self.weights[1:]) + self.weights[0]
        return step_function(summation)

    def train(self, training_inputs, labels, epochs=10):
        for _ in range(epochs):
            for inputs, label in zip(training_inputs, labels):
                prediction = self.predict(inputs)
                # Update weights and bias
                ## Weight
                self.weights[1:] += self.learning_rate * (label - prediction) * inputs
                ## Bias
                self.weights[0] += self.learning_rate * (label - prediction)

22.3 Execute

22.3.1 AND Logic Gait

# Training data (AND logic gate)
training_inputs = np.array([[0, 0], 
                            [0, 1], 
                            [1, 0], 
                            [1, 1]])
labels = np.array([0, 0, 0, 1])  # AND gate outputs

# Initialize perceptron
perceptron = Perceptron(input_size=2)

# Train perceptron
perceptron.train(training_inputs, labels, epochs=10)

# Test the perceptron
test_inputs = np.array([[0, 0], [0, 1], [1, 0], [1, 1]])
for inputs in test_inputs:
    print(f"Input: {inputs} -> Output: {perceptron.predict(inputs)}")

Input: [0 0] -> Output: 0
Input: [0 1] -> Output: 0
Input: [1 0] -> Output: 0
Input: [1 1] -> Output: 1

22.3.2 OR Logic Gait

# Training data (OR logic gate)
training_inputs = np.array([[0, 0], 
                            [0, 1], 
                            [1, 0], 
                            [1, 1]])
labels = np.array([0, 1, 1, 1])  # OR gate outputs

# Initialize perceptron
perceptron = Perceptron(input_size=2)

# Train perceptron
perceptron.train(training_inputs, labels, epochs=10)

# Test the perceptron
test_inputs = np.array([[0, 0], [0, 1], [1, 0], [1, 1]])
for inputs in test_inputs:
    print(f"Input: {inputs} -> Output: {perceptron.predict(inputs)}")

Input: [0 0] -> Output: 0
Input: [0 1] -> Output: 1
Input: [1 0] -> Output: 1
Input: [1 1] -> Output: 1