Learning Strategies through Reinforcement Learning
|
August 31, 2018
Reinforcement learning can be used to teach computers to perform complex tasks. In this lecture, I discuss two of my board game + reinforcement learning projects as a guest lecturer for STAT 385 at University of Illinois at Urbana-Champaign.
What Kinds of Fireworks Do We Celebrate With?
|
July 02, 2018
What kinds of fireworks do people use most often on Fourth of July in the US? With some survey data and weighting techniques, we can see some general statistics about fireworks usage.
Wordclouds of America
|
July 02, 2018
Wordclouds of how Americans describe America
Fixing Survey Samples by Raking Weights
|
June 24, 2018
If your sample populations are skewed by gender, race, age group, or any other segment, you can use raking to weight your data and get more accurate estimates.
What do People Do for Their Moms on Mothers Day?
|
May 13, 2018
What do people do for their moms on Mother's Day? I sampled a small group of people and got a rough idea of different ways people show their love and appreciation.
Reinforcement Learning for the Game of Splendor
|
May 04, 2018
Neural networks and reinforcement are used to teach a computer how to play the board game of Splendor. The process of training the network and its architecture are explained.
The Community of Garlicoin, the New Meme Cryptocurrency
|
April 09, 2018
Garlicoin is the hottest new meme cryptocurrency. I surveyed about 200 of its enthusiasts to get a good idea of what the community looked like and what they thought about the cryptocurrency.
Visualizing the IHSA State Cross-Country Meet
|
April 07, 2018
An analysis of how runners perform in the state IHSA cross-country meet and what the top runners look like in terms of pacing strategy. Also, some old-school footage from a while ago.
Exploring Data with Generative Clustering
|
January 09, 2018
Clustering is a common machine learning technique applied to data for a variety of reasons, including dimensionality reduction, finding similar objects, and discovering important features. Here I demonstrate how generative clustering can be used with the Iris data set.
Visualizing My Runs in 2017
|
January 01, 2018
A visualization of my running from 2017 using ggplot2.
Unpleasant Statistics: Santa Causes Kids to Turn Away From Christianity
|
December 23, 2017
What are the holidays without abuse of statistical techniques? According to a recent survey, kids being told that they receive gifts from Santa are up to 150% more likely to turn away from Christianity as an adult.
Analyzing and Clustering Christmas Foods, Drinks, and Desserts
|
December 22, 2017
When celebrating Christmas, most people think of a large feast as part of the celebration. In the fourth part of my Christmas article series, I look at what foods are common across different regions of the US. Clustering also shows interesting relationships between different foods and drinks.
Word Clouds of Christmas
|
December 21, 2017
Visualizations of how people describe Christmas using word clouds.
When do Kids Stop Believing in Santa?
|
December 20, 2017
When do kids stop believing in Santa? Are there any backgrounds more at risk for not believing in Santa as long? I explore these questions using a Christmas survey in part 2 of my series of Christmas articles.
Christmas Survey Results Part 1
|
December 19, 2017
How do people celebrate Christmas? This is the first article in a series that looks at trends across different groups of people, where I look at more general aspects of the questions asked.
Overlaying Density Heatmaps on Geographic Maps in R
|
December 15, 2017
In this example, I use noise complaint data from New York City to demonstrate how you can plot densities of events on a map, as well as how extreme the averages are.
How to use IPython Notebooks in Blog Posts
|
November 08, 2017
You can convert IPython notebooks to html with the command-line to insert them into your blog/website, and use a stylesheet provided here for proper formatting and syntax highlighting.
Reinforcement Learning Demo with Keras
|
November 05, 2017
Keras, a TensorFlow-based neural network library in Python, can be used to solve reinforcement learning tasks. In this demonstration, I demonstrate one method of solving a game to improve the odds of winning.
Suggestions for Making Your R Code Spookier
|
October 25, 2017
The air is getting colder, and sometimes you just want to add some pizzazz to your R code. Here are some tips for making it spookier this frightful season.
When Leverage Overshadows Regularization
|
October 18, 2017
Regularization is an effective way of preventing overfitting in a model. Highly influential points in a data set can create a large amount of variation in estimates despite its presence.