Scribd
Upload
9 views2 pages

SC Practical 3 4

The document outlines two practical exercises involving the implementation of logical functions using computational models. The first exercise demonstrates generating an OR function using linear separability, while the second focuses on creating an AND-NOT function using a perceptron network. Both exercises include code snippets and explanations of the decision boundaries and training processes.

Uploaded by

ikudi098
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
9 views2 pages

SC Practical 3 4

The document outlines two practical exercises involving the implementation of logical functions using computational models. The first exercise demonstrates generating an OR function using linear separability, while the second focuses on creating an AND-NOT function using a perceptron network. Both exercises include code snippets and explanations of the decision boundaries and training processes.

Uploaded by

ikudi098
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

Practical No.

3
Aim:-Generate OR function using linear sepratability.
def or_gate(x1, x2):

point1 = (-1, 0)

point2 = (0, -1)

m = (point2[1] - point1[1]) / (point2[0] - point1[0])

c = point1[1] - m * point1[0]

w1, w2, b = 1, 1, 1

decision_boundary_x2 = -w1 / w2 * x1 - b / w2

linear_combination = w1 * x1 + w2 * x2 + b

output = 1 if linear_combination >= 0 else 0

print(f"Decision Boundary: x2 = {-w1/w2:.2f} * x1 + {-b/w2:.2f}")

print(f"Input: ({x1}, {x2}) => Linear Combination: {linear_combination:.2f} => Output: {output}")

return output

test_inputs = [(-1, -1), (-1, 1), (1, -1), (1, 1)]

print("OR Gate Output:")

for x1, x2 in test_inputs:

or_gate(x1, x2)

Output:-
Practical No. 4
Aim:-Generate AND-NOT function using Perceptron network.
import numpy as np

def perceptron(X, w, b):

z = np.dot(X, w) + b

return 1 if z >= 0 else -1

def train_perceptron(X, y, learning_rate=1, epochs=100):

n_samples, n_features = X.shape

w = np.zeros(n_features)

b=0

for _ in range(epochs):

for i in range(n_samples):

y_pred = perceptron(X[i], w, b)

if y[i] * y_pred < 0:

w += learning_rate * y[i] * X[i]

b += learning_rate * y[i]

return w, b

X = np.array([[-1, -1], [-1, 1], [1, -1], [1, 1]])

y = np.array([-1, -1, 1, -1])

w, b = train_perceptron(X, y)

print("Trained weights:", w)

print("Trained bias:", b)

Output:-

You might also like