Machine Learning , IOT , Microservices , python

sigmoid reLU

 install - python numpy import numpy as np x = [[1, 5 ,6],[7, 8 ,9],[5, 4, 3]] y = [[1,2],[2,3],[1,5]]       np.dot(x, y) result -  array([[17, 47],        [32, 83],        [16, 37]])    

 The idea is to understand how u can create a sample for stochastic gradient descent using python , numpy and some basic maths. so what is gradient descent  u might be bored with the term and it is always boring with visualization here i will run through a sample using python and plot that in mat plot lib for visual. matplot lib is another library u can install on the go and it is like a simple x,y graph that we used in our school days.don't worry this is pretty simple. 1.install python - https://www.python.org/downloads/ if you are using windows it will be a exe run that . once installed type in command line   since the function is  y = w1* x1 +w2 * x2 +b we will use the know  mean square error loss function  mae  = (y - y_hat)**2 next step would be to calculate partial derivatives for w1 , w2 , b  with respect to y dy/dw1 = x1 dy/dw2 = x2  dy/db = 1 h = (y - y_hat) ** 2  h = u **2 , u = y - y_hat dh/du = 2u = 2 (y - y_hat) du/dy = 1 by chain rule dh/dy = dh/du * du/dy dh/dy = 2

import numpy as np import matplotlib.pyplot as plt import cv2 as cv #this program conversts color of certain sections of image #each pixel is checked for the r g b and modified using a numpy array image = cv.imread('rg.png') #print(image.shape) #print(np.asarray(image)) width , height , channels = image.shape #print(width) #print(height) #print(channels) plt.imshow(image) plt.show() #print(image[29][29]) zero_array = np.zeros((2, 3, 3)) for pixeli in range(width):     #print(pixeli)     for pixelj in range(height):        # print(pixeli,pixelj)         #print(image[pixeli][pixelj])         pixelvalue = image[pixeli][pixelj]         #print(pixelvalue)         if pixelvalue[0] == 76 and pixelvalue[1] == 177 and pixelvalue[2] == 34:             #print('mach')             r = 0             g = 0             b = 0             image[pixeli][pixelj] = [r, g, b]   plt.imshow(image) plt.show() The pixel level color are changed as y

Simply called as Conv net , neural networks dealing with images simply called convnet. use case : Models can be created using Conv net and trained using data.     Simple convnet can be created using tensorflow