implementation of perceptron in python

In [2]:
# -*- coding: utf-8 -*-
# @Author: Sijan
# @Date:   2019-04-01

from random import randint


def step_function(result):
    """
    Simple linear function which will be activated if the value is greater than 0.
    """
    if result > 0:
        return 1
    return 0


class Perceptron:
    """
    Perceptron class defines a neuron with attributes : weights, bias and learning rate.
    """

    def __init__(self, input_size):
        self.learning_rate = 0.5
        self.bias = randint(0, 1)
        self.weights = [randint(0, 1) for _ in range(input_size)]


def feedforward(perceptron, node_input):
    """
    Implements product between input and weights
    """
    node_sum = 0
    node_sum += perceptron.bias

    for index, item in enumerate(node_input):
        # print('input node is', item)
        node_sum += item * perceptron.weights[index]

    return step_function(node_sum)


def adjust_weight(perceptron, node_input, error):
    """
    Adjust weightage based on error. It simply scales input values towards right direction.

    """
    for index, item in enumerate(node_input):
        perceptron.weights[index] += item * error * perceptron.learning_rate

    perceptron.bias += error * perceptron.learning_rate


def train(perceptron, inputs, outputs):
    """
    Trains perceptron for given inputs.
    """
    for training_input, training_output in zip(inputs, outputs):
        actual_output = feedforward(perceptron, training_input)
        desired_output = training_output
        error = desired_output - actual_output
        adjust_weight(perceptron, training_input, error)
        print('weight after adjustment', perceptron.weights)
        print('bias after adjustment', perceptron.bias)


def predict(perceptron, test_input, test_output):
    """
    Predicts new inputs.
    """
    prediction = feedforward(perceptron, test_input)

    # if test_input[1] == test_output:
    print('input :%s gives output :%s' % (test_input, prediction))
    print('input :%s has true output :%s' % (test_input, test_output))


if __name__ == '__main__':

    train_inputs = [(0, 0), (0, 1), (1, 0), (1, 1)]
    train_outputs = [0, 0, 0, 1]

    # train perceptron
    perceptron = Perceptron(2)
    epochs = 10

    for _ in range(epochs):
        train(perceptron, train_inputs, train_outputs)

    # test perceptron
    test_input = (1,1)
    test_output = 1
    print('...................................')
    print('...................................')
    predict(perceptron, test_input, test_output)
weight after adjustment [0.0, 0.0]
bias after adjustment 0.0
weight after adjustment [0.0, 0.0]
bias after adjustment 0.0
weight after adjustment [0.0, 0.0]
bias after adjustment 0.0
weight after adjustment [0.5, 0.5]
bias after adjustment 0.5
weight after adjustment [0.5, 0.5]
bias after adjustment 0.0
weight after adjustment [0.5, 0.0]
bias after adjustment -0.5
weight after adjustment [0.5, 0.0]
bias after adjustment -0.5
weight after adjustment [1.0, 0.5]
bias after adjustment 0.0
weight after adjustment [1.0, 0.5]
bias after adjustment 0.0
weight after adjustment [1.0, 0.0]
bias after adjustment -0.5
weight after adjustment [0.5, 0.0]
bias after adjustment -1.0
weight after adjustment [1.0, 0.5]
bias after adjustment -0.5
weight after adjustment [1.0, 0.5]
bias after adjustment -0.5
weight after adjustment [1.0, 0.5]
bias after adjustment -0.5
weight after adjustment [0.5, 0.5]
bias after adjustment -1.0
weight after adjustment [1.0, 1.0]
bias after adjustment -0.5
weight after adjustment [1.0, 1.0]
bias after adjustment -0.5
weight after adjustment [1.0, 0.5]
bias after adjustment -1.0
weight after adjustment [1.0, 0.5]
bias after adjustment -1.0
weight after adjustment [1.0, 0.5]
bias after adjustment -1.0
weight after adjustment [1.0, 0.5]
bias after adjustment -1.0
weight after adjustment [1.0, 0.5]
bias after adjustment -1.0
weight after adjustment [1.0, 0.5]
bias after adjustment -1.0
weight after adjustment [1.0, 0.5]
bias after adjustment -1.0
weight after adjustment [1.0, 0.5]
bias after adjustment -1.0
weight after adjustment [1.0, 0.5]
bias after adjustment -1.0
weight after adjustment [1.0, 0.5]
bias after adjustment -1.0
weight after adjustment [1.0, 0.5]
bias after adjustment -1.0
weight after adjustment [1.0, 0.5]
bias after adjustment -1.0
weight after adjustment [1.0, 0.5]
bias after adjustment -1.0
weight after adjustment [1.0, 0.5]
bias after adjustment -1.0
weight after adjustment [1.0, 0.5]
bias after adjustment -1.0
weight after adjustment [1.0, 0.5]
bias after adjustment -1.0
weight after adjustment [1.0, 0.5]
bias after adjustment -1.0
weight after adjustment [1.0, 0.5]
bias after adjustment -1.0
weight after adjustment [1.0, 0.5]
bias after adjustment -1.0
weight after adjustment [1.0, 0.5]
bias after adjustment -1.0
weight after adjustment [1.0, 0.5]
bias after adjustment -1.0
weight after adjustment [1.0, 0.5]
bias after adjustment -1.0
weight after adjustment [1.0, 0.5]
bias after adjustment -1.0
...................................
...................................
input :(1, 1) gives output :1
input :(1, 1) has true output :1
In [ ]:
 

Comments

Comments powered by Disqus