Simple Implementation of a Neural Network

Python3

import numpy as np
 
# array of any amount of numbers. n = m
X = np.array([[1, 2, 3],
              [3, 4, 1],
              [2, 5, 3]])
 
# multiplication
y = np.array([[.5, .3, .2]])
 
# transpose of y
y = y.T
 
# sigma value
sigm = 2
 
# find the delta
delt = np.random.random((3, 3)) - 1
 
for j in range(100):
   
    # find matrix 1. 100 layers.
    m1 = (y - (1/(1 + np.exp(-(np.dot((1/(1 + np.exp(
        -(np.dot(X, sigm))))), delt))))))*((1/(
            1 + np.exp(-(np.dot((1/(1 + np.exp(
                -(np.dot(X, sigm))))), delt)))))*(1-(1/(
                    1 + np.exp(-(np.dot((1/(1 + np.exp(
                        -(np.dot(X, sigm))))), delt)))))))
 
    # find matrix 2
    m2 = m1.dot(delt.T) * ((1/(1 + np.exp(-(np.dot(X, sigm)))))
                           * (1-(1/(1 + np.exp(-(np.dot(X, sigm)))))))
    # find delta
    delt = delt + (1/(1 + np.exp(-(np.dot(X, sigm))))).T.dot(m1)
 
    # find sigma
    sigm = sigm + (X.T.dot(m2))
 
# print output from the matrix
print(1/(1 + np.exp(-(np.dot(X, sigm)))))

Output:

[[0.99999325 0.99999375 0.99999352]
 [0.99999988 0.99999989 0.99999988]
 [1.         1.         1.        ]]

What is a neural network?

Neural Networks are computational models that mimic the complex functions of the human brain. The neural networks consist of interconnected nodes or neurons that process and learn from data, enabling tasks such as pattern recognition and decision making in machine learning. The article explores more about neural networks, their working, architecture and more.

Table of Content

Evolution of Neural Networks
What are Neural Networks?
How does Neural Networks work?
Learning of a Neural Network
Types of Neural Networks
Simple Implementation of a Neural Network

Simple Implementation of a Neural Network

Python3

What is a neural network?

Similar Reads