Blog

Reproducible Hyper Parameter Sweeps in Machine Learning

In the past couple weeks I've been working on writing machine learning code in python with the following goals:

  1. Make experiments easy to reproduce (or retroactively debug). Primarily, this means saving the configuration and the code as it was at the time it was run.
  2. Make it easy to run …

Read More

Debugging Machine Learning Code

Developing new machine learning code is often error prone and takes many iterations of the write-run-debug loop. In this context, I specifically refer to saving time fixing errors that crash the program--not than those that cause models to be incorrect in subtle ways (for that, see Andrej Karpathy's blog post …

Read More

Riot Games Data Science Internship Video

Summer 2017 I was a data science intern at Riot Games. It was an amazing experience for many reasons, and I'm excited to share the video that Riot Games produced featuring interviews with all the data science interns!

More about the internship, and applying at the …

Read More

Entropy and KL Divergence

Description: Intuitive introduction to what the Kl divergence is, how it behaves, and why its useful

Introduction

The KL divergence is short for the Kullback-Leibler Divergence discovered by Solomon Kullback and Richard Leibler in 1951. Semantically, divergence means the amount by which something is diverging, and diverging in turn means to lie in different directions from a different point. In the case of KL divergence we …

Read More

Video Talk: Playing Trivia Games by Playing the Wikipedia Game

Description: Video presentation of a new network science based technique inspired by the Wikipedia Game for question answering.

In this video talk I discuss recent work which uses a network science technique inspired by the Wikipedia Game to answer trivia questions. This was also a final course project for Aaron Clauset's Network Models course

This research is supported by an NSF Grant, and more …

Read More

Lecture: Using Machine Learning to play Trivia Games

Description: Presentation slides from CU Boulder lecture on AI for trivia games

On October 25, 2016 I gave a guest lecture to the machine learning course at CU Boulder. The lecture was an adapted version of my STEMinar talk earlier this year, and aimed at an audience of students just getting into machine learning.The lecture highlights our research's group work on …

Read More