Here we’re going to be going through the steps to implement a simulation of a variant of Liar’s Dice called Skull (rules can be found here). This game can be played with a standard playing card deck and is a game of incomplete information and deception similar to poker. All...
[Read More]
Robust Curvature Estimation
Creating a novel algorithm for estimating curvature of surfaces and high dimesional data manifolds
Computing curvature is a common problem that has applications in a variety of areas from computational physics to computer graphics to machine learning. In this post I’m going to cover the main ideas behind my recent paper in which I propose a novel algorithm (VWME) for robustly computing curvature.
[Read More]
A data science approach to choosing a Valorant team comp (Part 2)
Applying statistics to determine the best agents in Valorant
We begin by continuing from where we left off in the previous post. We’ll be performing some further analysis on the Valorant competitive data we processed and revisit our goal of determining the best competitive team composition.
[Read More]
A data science approach to choosing a Valorant team comp (Part 1)
Cleaning and clustering our data for easy analysis and visualization
In this post we’ll be going through an SQL database of professional valorant stats, process that data, and use the results to try and determine what the best team comps are. Before we begin, if you want to follow along, the dataset can be downloaded here.
[Read More]
Low-rank Matrices and Inpainting
Reconstruct images using signal processing and machine learning
Before we begin with the mathematics we should start first by defining the problem and the terms associated with it. Image inpainting is the reconstruction of a corrupted or damaged image through some means. In this post I will be discussing an interesting method that can be used to reconstruct...
[Read More]