Tag Archives: machine learning

Decision Trees for Linguists Pt. 1 – A super simple example

Continued in Part 2. Purity If I have a basked of apples, and only apples, then it’s considered “pure.” If I put a banana in the basket, I can no longer call it a basket of bananas, and it’s now considered “impure.” Purity is a measure of how varied a set is. A purity of… Read More »

One-Shot Learning: The End of Big Data?

Recently, a Bayesian probabilistic model outperformed neural networks and humans  in classifying written letters using very small datasets. One-shot learning is a type of machine learning that learns an object class after just one or a few examples. This is similar to how humans learn to identify objects, creating a rich, abstract template of objects… Read More »