talks about machine learning ,IOT and web apps
Posts
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
Raspberry pi is a computer which can easily run on linux os uses: can be used as a controller for projects controller meaning send and receive data using raspberry pi to devices for testing. can be used for developing prototypes. simply buy and start exploring the world simple as that. https://www.raspberrypi.org/products/ if your are interested in LINUX install in pi and use as a desktop computer. https://ubuntu.com/download/raspberry-pi https://ubuntu.com/download/iot Buy the latest raspberry -5 Select your country and reseller to buy directly from the reseller. https://www.raspberrypi.com/products/raspberry-pi-5/ Raspberry keyboard can be bought but my experience with the keyboard was boring and some keys were not working It’s better to use other keyboards rather than this. buy the new raspberry with higher configuration 8 Gb/quad core enjoy - https://www.raspberrypi.com/products/raspberry-pi-400/
http://www.nltk.org/book/ Soon start downloading the toolkit and get familiar with the corpus. corpus is nothing but a data set used for training.