FastML

Machine learning made easy

Two faces of overfitting

Overfitting is on of the primary problems, if not THE primary problem in machine learning. There are many aspects to it, but in a general sense, overfitting means that estimates of performance on unseen test examples are overly optimistic. That is, a model generalizes worse then expected.

We explain two common cases of overfitting: including information from a test set in training, and the more insidious form: overusing a validation set.

Revisiting Numerai

In this article, we revisit Numerai and their weekly data science tournament. New developments include a much larger dataset, tougher requirements for models, and bigger payouts.

It’s embarassing, really

In August, we published the first version of goodbooks-10k, a new dataset for book recommendations. By pure chance, that coincided with a proclamation of Kaggle Datasets Awards. Oh, how we hoped to get one!

Introduction to pointer networks

Pointer networks are a variation of the sequence-to-sequence model with attention. Instead of translating one sequence into another, they yield a succession of pointers to the elements of the input series. The most basic use of this is ordering the elements of a variable-length sequence or set.

Project RHUBARB: predicting mortality in England using air quality data

Once again we beat the benchmark in a Kaggle competition. The goal of the contest at hand was to forecast mortality rate in England using Copernicus Atmosphere Monitoring Service data on air quality. Specifically, to forecast mortality caused by cancer and cardiovascular diseases. The competition represents the “in class” category, because the data is publicly available somewhere on the internets. Still, the winner got a Raspberry Pi.

Tuning hyperparams fast with Hyperband

Hyperband is a relatively new method for tuning iterative algorithms. It performs random sampling and attempts to gain an edge by using time spent optimizing in the best way. We explain a few things that were not clear to us right away, and try the algorithm in practice.

Data in, predictions out

With many implementations of machine learning algorithms it is entirely unclear how to train them on one’s own data and then how to get predictions. This is an area where AI researchers have a lot of catching up to do with lessons long ago learned in computer science.

On chatbots

Chatbots seem to be all the craze these days. Why don’t we take a look at this fascinating topic. A warning, though: this article contains strong opinions.