Scribd Logo
Upload

Welcome to Scribd!

  • 24 views

    Experiment 3 Perceptron Learning Rule:: Input: Import Numpy As NP

    Uploaded by

    mridul
    The document describes an experiment involving perceptron learning rules for binary classification. It defines functions for an activation function and a perceptron model. It then trains the perceptron model on an input dataset X with the corresponding labels Y over 10 epochs. It prints the learned weights w1, w2, and wb of the perceptron model after training.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd

    Experiment 3 Perceptron Learning Rule:: Input: Import Numpy As NP

    Uploaded by

    mridul
    24 views2 pages
    The document describes an experiment involving perceptron learning rules for binary classification. It defines functions for an activation function and a perceptron model. It then trains the perceptron model on an input dataset X with the corresponding labels Y over 10 epochs. It prints the learned weights w1, w2, and wb of the perceptron model after training.

    Original Title

    2017UIT2532_exp3.pdf

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    The document describes an experiment involving perceptron learning rules for binary classification. It defines functions for an activation function and a perceptron model. It then trains the perceptron model on an input dataset X with the corresponding labels Y over 10 epochs. It prints the learned weights w1, w2, and wb of the perceptron model after training.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    24 views2 pages

    Experiment 3 Perceptron Learning Rule:: Input: Import Numpy As NP

    Uploaded by

    mridul
    The document describes an experiment involving perceptron learning rules for binary classification. It defines functions for an activation function and a perceptron model. It then trains the perceptron model on an input dataset X with the corresponding labels Y over 10 epochs. It prints the learned weights w1, w2, and wb of the perceptron model after training.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    of 2

    Shruti Garg

    2017UIT2532

    Experiment 3
    Perceptron Learning Rule:
    Input:

    import numpy as np

    R = int(input("Enter the number of rows:"))


    C = int(input("Enter the number of columns:"))

    print("Enter the inputs in a single line (separated by space): ")

    entries = list(map(int,
    input().split())) x =
    np.array(entries).reshape(R, C)
    print(x) # np.ones((2, 1))

    gate = int(input("Enter 1 for OR, 2 for AND, 3 for NOR, 4 for NAND and 5 for
    XOR: ")) if gate==1:
    y=
    np.logical_or(x[:,0],x[:,1]) if
    gate==2:
    y=
    np.logical_and(x[:,0],x[:,1]) if
    gate==3:
    y=
    np.logical_not(np.logical_or(x[:,0],x[:,1])) if
    gate==4:
    y=
    np.logical_not(np.logical_and(x[:,0],x[:,1])) if
    gate==5:
    y = np.logical_xor(x[:,0],x[:,1])

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


    [-1, 1, 1],
    [1, -1, 1],
    [1, 1, 1]])

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


    Shruti Garg
    2017UIT2532

    def
    activation(x):
    if x == 0:
    return 0
    return 1 if x > 0 else -1

    def perceptron(x, y,
    epochs): alpha = 1
    w = np.zeros((x.shape[1],
    1)) for e in
    range(epochs): for i in
    range(4):
    y_pred = activation(np.dot(x[i],
    w)) if(y_pred != y[i]): w
    += alpha * y[i] * x[i].reshape(3, 1)
    return w

    w = perceptron(X, Y, 10)
    print(f"w1 = {w[0][0]} w2 = {w[1][0]} wb ={w[2][0]}")

    Output:

    You might also like