Social network analysis involves studying patterns in large real life networks that are comprised of millions of nodes. If you have a basic knowledge of graph theory, you can perform these analyses.

The digital world has opened up a totally different way of creating relationships. It’s also unleashed an ocean of data we can analyze to get a better understanding of human behavior.

Social media data refers to all of the raw insights and information collected from an individual’s social media activity. We can create networks from these social media activities to get a better perception of that individual.

These networks can range widely and might include your Facebook friends, the products you recently purchased on Amazon, the tweets you liked or retweeted, your favorite food you ordered from Zomato, the search you made on Google, or the image you recently liked on Instagram. …

A drunk man standing on a cliff, takes steps randomly left and right. Each step he takes has a probability of going left and a probability of going right and the size of each step is same. If the drunk man is allowed to randomly step indefinitely, what will be the probability that he falls off the cliff?

*Any guesses? Well, let’s again have a glimpse of this problem through “Random Walk”.*

The **Random Walk** theory is based on the irregular motion of the individual pollen particles, studied by botanist, Mr. Robert Brown in 1828. In the process of researching on a random walk, scientists like Einstein and Smoluchowski studied similar subjects like random process, random noise, spectral analysis, and stochastic equations. …

Support Vector Machine (SVM) is a supervised classifier and is defined by a separating hyperplane. In other words, given a set of labeled data, SVM generates an optimal hyperplane in the feature space which demarcates different classes.

**Confusing, isn’t it? Let’s understand it in layman's terms.**

Suppose, you have a given set of points of two types (say □ and ○) on a paper which are linearly separable. The job of SVM is to find a straight line that asserts the set into two homogeneous types, and which is also situated as far as possible from all those points.

Evidently, both straight-line ‘A’ and ‘B’ separate the two types of points as desired. However, ‘A’ is precisely situated as far as possible from all those points. SVM, as a tool, will elect ‘A’ as the separating hyperplane. In the image, the light blue periphery around lines ‘A’ and ‘B’ is called ‘Margin’. It is defined as the distance from the hyperplane to the nearest point, multiplied by 2. In simpler terms, the hyperplane will stay in the middle of the margin. The higher margin will give the optimal hyperplane. …

If you’re impatient, scroll to the bottom of the post for the Github Repos

This is Part 2 of Sudoku Solver. Make sure you got a glimpse of Part 1. So moving ahead, till now we have preprocessed an image i.e., take an image and perform a crop and warp perspective transform. Now we need to extract the numbers and solve the sudoku.

So, our next task is to extract each number from the image, identify the number and save it into a 2D matrix.

For digit recognition, we will be training neural network over MNIST dataset containing 60,000 images of digits from 0 to 9. …

Extract and solve the sudoku from an image.

I, like many others, enjoy solving new puzzles and questions. During my school days, each morning I used to do The Times of India’s sudoku. Everyone knows how to solve sudoku but have you ever wondered that you can get to the solution without even scratching your head once. You just have to click the picture of the sudoku and it should calculate the solution for you.

Peter Norvig in his Solving Every Sudoku Puzzle gives a beautiful summary of the game’s rule in just one sentence.

A puzzle is solved if the squares in each unit are filled with a permutation of the digits 1 to 9. …

About