Well, airflow can’t work on windows directly. I was not able to run airflow with docker as well. Now what? I am sharing a possible way to get airflow working on windows, that worked for me.

- Turn Window Subsystem For Linux

a. Setting >> Apps >> “Related settings”

b. Click the**Programs and Features**option

c. Click the**Turn Windows features on or off**option

d. Check the**Windows Subsystem for Linux**option

2. Install Ubuntu Linux

a. Go to Microsoft Store

b. Install Ubuntu ( I downloaded from Canonical Group Limited)

c. …

Learn and implement Haar cascade classifier in projects…

The Viola-Jones object detection framework is a machine learning approach for object detection, proposed by Paul Viola and Micheal Jones in 2001. This framework can be trained to detect almost any object, but this primarily solves the problem of face detection in real-time. This algorithm has four steps.

Objects are classified on very simple features as a feature to encode ad-hoc domain knowledge and operate much faster than pixel system. The feature is similar to haar filters, hence the name ‘Haar’. An example of these features is a 2-rectangle feature, defined as…

*An approach to understanding pooling layers and effect on backpropagation*

CNNs work on a weight sharing strategy, neurons are able to perform convolutions on the data with the convolution filter being formed by the weights. Pooling operation then follows which reduces the spacial size of the representation thus reducing the amount of computation and parameters in the network. Pooling layer also helps to control overfitting.

No learning takes place on the pooling layers

Pooling units are obtained using functions like max-pooling, average pooling and even L2-norm pooling. …

Random number have lots of application like, cryptography, game and Neural Network. Here we’ll discuss and identify different methods for generating random numbers in NumPy module in python.

import numpy as np

** numpy.random.random (size)**— Return random floats in the half-open interval [0.0, 1.0), ie

>>>np.random.random((2,2))array([[ 0.66032591, 0.91397527],

[ 0.63366556, 0.36594058]])

** numpy.random.randint(low, high, size, dtype=int) **— Return random integers from

>>> np.random.randint([1, 3, 5, 7], [[10], [20]], dtype=np.uint8)array([[ 8, 6, 9, 7],

[ 1, 16, 9, 12]], dtype=uint8)

** numpy.random.randn(d1,d2,..dn)** …

A question that all the Data Science learners have is, why is there a need to normalize data. Here we will discuss the answer and get the intuition of the mechanics.

What happens when things don’t work out as planned…

So I had an idea to design an android application to measure lengths just by placing your phone at the two side and use the acceleration value to calculate displacement. **Simple Kinematics !!**

Aim is to code logistic regression for binary classification from scratch, using the raw mathematical knowledge and concept that we have.

This is second part of series on Logistic Regression:

- Fundamental of Logistic Regression
- Coding Logistic Regression in Python From Scratch

First we need to import numpy. NumPy is a class to handle complex array calculation and reduces the time of calculations quickly. You can learn about numpy *here*.

`import numpy as np`

To package the different methods we need to create a class called “MyLogisticRegression”. The argument taken by the class are: **learning_rate**- It determine the learning speed of…

*Here we’ll learn binary classification using logistic regression*

This is second part of series on Logistic Regression:

- Fundamental of Logistic Regression
- Coding Logistic Regression in Python From Scratch

The logistic regression is a supervised learning system borrowed from the concepts of statistics. The name “Logistic” is taken from the Logistic Function also called the sigmoid function.

Designing an automatic flushing solutions.

*My grandfather kept forgetting to flush the toilet after using it, which highly affects his hygiene.*

This is how the automatic flushing and cleaning systems, must be working in malls. Even though, it was a very trivial problem, but in solving it, I got to learn a few crucial things. Product design experience is the one crucial experience, which I will share here.

There were two hikers in Alaskan wilderness, got lost due to a terrible blizzard and its fifty degrees freezing. So one who was religious guy started praying God please help me. However since there was none the other option, his atheist friend also started praying “Oh God! If there is a God, please help me. I am lost in this blizzard and I’m going die if you will not help me”.

Out of nowhere couple of Eskimos came by, and showed them the way to there camp. On the way the religious guy startled, “so now you believe that the…

I believe in an altruistic world, where creativity and imagination replace repetitive work