Blog

With the interest and hype being what it is, in one sense it’s never been a better time to be studying AI. You can see this in how many people want to be associated with AI. Looking at a few examples from ND, NYU, and Penn ([1], [2]), we see that faculty working in or around AI span a variety of disciplines.

I just finished reading Arnold Schwarzenegger’s new book, Be Useful. Below are his seven tools for usefulness.

(I never thought I would write a title like that)

This post is meant as a companion to our EMNLP 2016 paper “Building an Evaluation Scale using Item Response Theory”. It’s quite a bit overdue, but hopefully this post will be useful to those who haven’t seen IRT before.

I was preparing my slides for my recent MLFL talk, and I came across this great page on How to give a great presentation by Simon Peyton Jones at MSR. First off, it was a huge help in getting ready for the presentation, I was still very nervous but the tips in the slides were a big help.

Neural networks are all the rage these days, with a huge number of examples of their capabilities around the web. One particular type is the Long Short-Term Memory Recurring Neural Network (LSTM RNN). I’ll leave the explanation of how they work to more qualified people, but I wanted to show off a particularly interesting application of the technology.

Every once in a while I’m going to write a post about something I learned in my Machine Learning course here at UMass. I’d like to do one post per lecture, but I’m late out of the gate, so it might be less frequent. These posts aren’t intended to be thorough explanations of particular topics, but instead will be relatively high-level overviews, with a simple example to illustrate the concept. That’s the plan anyway. Comments or corrections are welcome and encouraged.