“Such a shovel, it seemed a waste not to use it.”
― Daniel Kraus, Rotters
In the message broker RabbitMQ, a typical setup is to deploy a single RMQ instance that resides in a box. The job of RMQ is to deal with incoming messages and make sure these are forwarded to the correct destination.
The publisher sends the messages to an exchange which are the message routing agents. The exchange routes the messages based on routing keys to different queues. Each queue has consumers attached who will consume the messages and process them.
Most of us have created our own customized bitmoji and used them across different social media apps. Those bitmoji are personalized for a particular user. But have you ever wondered how to generate bitmoji that doesn't belong to any human face? Well, let's explore how GANs do the job for us.
Generative Adversarial Networks are one of the most interesting ideas in computer science today. GANs can generate images from garbage datasets. GANs were developed by Ian J. Goodfellow in 2014. It consists of two neural networks which compete with each other to become more accurate in their prediction.
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.
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…
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.
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…
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…