Related Articles
Implementation of Perceptron Algorithm for XNOR Logic Gate with 2-bit Binary Input
• Last Updated : 13 Jul, 2020

In the field of Machine Learning, the Perceptron is a Supervised Learning Algorithm for binary classifiers. The Perceptron Model implements the following function: For a particular choice of the weight vector and bias parameter , the model predicts output for the corresponding input vector .

XNOR logical function truth table for 2-bit binary variables, i.e, the input vector and the corresponding output    001
010
100
111

We can observe that, Designing the Perceptron Network:

1. Step1: Now for the corresponding weight vector of the input vector to the OR and AND node, the associated Perceptron Function can be defined as:  2. Step2: The output from the OR node will be inputed to the NOT node with weight and the associated Perceptron Function can be defined as: 3. Step3: The output from the AND node and the output from NOT node as mentioned in Step2 will be inputed to the OR node with weight . Then the corresponding output is the final output of the XNOR logic function. The associated Perceptron Function can be defined as:  For the implementation, the weight parameters are considered to be and the bias parameters are .

Python Implementation:

 # importing Python libraryimport numpy as np  # define Unit Step Functiondef unitStep(v):    if v >= 0:        return 1    else:        return 0  # design Perceptron Modeldef perceptronModel(x, w, b):    v = np.dot(w, x) + b    y = unitStep(v)    return y  # NOT Logic Function# wNOT = -1, bNOT = 0.5def NOT_logicFunction(x):    wNOT = -1    bNOT = 0.5    return perceptronModel(x, wNOT, bNOT)  # AND Logic Function# w1 = 1, w2 = 1, bAND = -1.5def AND_logicFunction(x):    w = np.array([1, 1])    bAND = -1.5    return perceptronModel(x, w, bAND)  # OR Logic Function# here w1 = wOR1 = 1, # w2 = wOR2 = 1, bOR = -0.5def OR_logicFunction(x):    w = np.array([1, 1])    bOR = -0.5    return perceptronModel(x, w, bOR)  # XNOR Logic Function# with AND, OR and NOT  # function calls in sequencedef XNOR_logicFunction(x):    y1 = OR_logicFunction(x)    y2 = AND_logicFunction(x)    y3 = NOT_logicFunction(y1)    final_x = np.array([y2, y3])    finalOutput = OR_logicFunction(final_x)    return finalOutput  # testing the Perceptron Modeltest1 = np.array([0, 1])test2 = np.array([1, 1])test3 = np.array([0, 0])test4 = np.array([1, 0])  print("XNOR({}, {}) = {}".format(0, 1, XNOR_logicFunction(test1)))print("XNOR({}, {}) = {}".format(1, 1, XNOR_logicFunction(test2)))print("XNOR({}, {}) = {}".format(0, 0, XNOR_logicFunction(test3)))print("XNOR({}, {}) = {}".format(1, 0, XNOR_logicFunction(test4)))
Output:
XNOR(0, 1) = 0
XNOR(1, 1) = 1
XNOR(0, 0) = 1
XNOR(1, 0) = 0


Here, the model predicted output ( ) for each of the test inputs are exactly matched with the XNOR logic gate conventional output ( ) according to the truth table.
Hence, it is verified that the perceptron algorithm for XNOR logic gate is correctly implemented. My Personal Notes arrow_drop_up