The topic of how to create and maintain reproducible experiments has come up a few times recently. I've previously discussed ways to do reproducible hyper parameter sweeps and as part of that briefly discussed using anaconda environments…
Conducting a thorough literature review for a new idea is a critical yet difficult research skill to learn. Even now, for areas I'd like to think I have a good grasp on, its difficult not to miss something important; multiple times, I've…
AI2 recently released version of its excellent AllenNLP library. The goal of this (living) blog post is to list code and configuration changes I've made in my own code to migrate from to . While I was writing this, I also found that the…
In my last post on parameter sweeps, I mentioned that I found a nice way to combine AllenNLP and comet.ml. In this post, I'll share my code that does this via the (experimental) callback trainer. The release of AllenNLP is currently…
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…
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…
We have updated our project site for qanta.org with many more resources. Datasets: datasets.qanta.org AI Assisted Quiz Bowl Question Writing Events for 2019 Competition Leaderboard: leaderboard.qanta.org Baseline System Code…
The results of our NIPS 2017 Competition are now part of The Springer Series on Challenges in Machine Learning book. Our chapter, Human-Computer Question Answering: The Case for Quiz Bowl, is now available.
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! Click Image to Watch…
Intuitive introduction to what the Kl divergence is, how it behaves, and why its useful
In this snowpack lecture from an avalanche level 1 course organized by the Bryan Mountain Nordic Ski Patrol I talk about the ways that the snowpack changes over time, and how that impacts avalanche safety. Click Image to Watch
Video presentation of a new network science based technique inspired by the Wikipedia Game for question answering.
Presentation slides from CU Boulder lecture on AI for trivia games
How to make a python package to plot AWS Spot Price History and send it to Slack using Airflow
Presentation slides from CU Boulder STEMinar talk on question answering AI
Guide for creating website with Github Pages and Pelican
Using ScalaFunctional to do functional programming in Python