I’m excited to announce that the University of Sheffield’s Department of Computer Science will make two appointments in machine learning this year.

Old MacDonald had a farm. On that farm was a big field.

This evening I’m participating in a debate on AI. We get seven minutes each for our initial statement. This is the script for mine.

Dimensionality reduction is a critical component of any solution dealing with massive data collections. Being able to sift through a mountain of data efficiently in order to find the key descriptive, predictive, and explanatory features of the collection is a fundamental required capability for coping with the Big Data avalanche. Identifying the most interesting dimensions of data is especially valuable when visualizing high-dimensional (high-variety) big data.

The need for anomaly and change detection will pop up in almost any data driven system or quality monitoring application. Typically, there a set of metrics that need to be monitored and an alert raised if the values deviate from the expected. Depending on the task at hand, this can happen at individual datapoint level (anomaly detection) or population level where we want to know if the underlying distribution changes or not (change detection).

Yesterday, a coworker pointed me to a new paper by Jacob Westfall and Tal Yarkoni called “Statistically controlling for confounding constructs is harder than you think”. I quite like the paper, which describes some problems that arise when drawing conclusions about the relationships between theoretical constructs using only measurements of observables that are, at best, approximations to those theoretical constructs.

Summary: I learn best with toy code that I can play with. This tutorial teaches DeepMind’s Neural Stack machine via a very simple toy example, a short python implementation. I will also explain my thought process along the way for reading and implementing research papers from scratch, which I hope you will find useful.

Kia recommends that I get the oil in my 2009 Rio changed every 7,500 miles. But, anecdotally, it seemed that I always got better gas mileage right after an oil change than I did right before I was due for another one. So, I got to wondering - if an oil change costs $20, but saves me a few MPGs, is it cheaper overall to change my oil sooner than 7,500 miles? If so, where’s the optimal point?

I’m doing a public event for Science Week this year on 17th March in the Diamond building. More details and seat bookings are here

When faced with a new classification problem, machine learning practitioners have a dizzying array of algorithms from which to choose: Naive Bayes, decision trees, Random Forests, Support Vector Machines, and many others. Where do you start? For many practitioners, the first algorithm they reach for is one of the oldest in the field: logistic regression.