Category Archives: AI

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 »

N-Gram Tutorial in R

What are n-grams? N-grams of texts are extensively used in text mining and natural language processing tasks. They are basically a set of co-occurring words within a given window and when computing the n-grams you typically move one word forward. For example, for the sentence: “The cow jumps over the moon”. If N=2 (known as a… 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 »