/statlearn-read

Repository for the Statistical Learning of Reading project where (borrowing from Visual Neuroscience literature) ANN architectures are used to gain insight on how brain learns to read.

Primary LanguagePythonMIT LicenseMIT

Statistical Learning - Reading in Artificial Neural Networks

In this project we investigate whether ANN (in particular DCNN) trained on visual datasets (ImageNet) respond to reading task typical of the Statistical Learning framework express the same pattern sensitivity as found in human subject.

Dataset: Alien Language

Dataset consists of 23 made-up characters (taken from the Brussels Artificial Character set - BACS2-serif). Each 3-character word is composed by randomly sampling the characters such that two classes emerge on character-pair distribution: high-frequency and low-frequency.

Here is an example of a randomly sample 3-character word from the BACS2-serif character set.

  Example Word