Handwritten character recognition: nifty assignment
Gabriel J. Ferrer · Journal of computing sciences in colleges · 2010
In this Nifty Assignment, for use in an Artificial Intelligence course, students are given code for a GUI in which they can draw and save handwritten characters on a 20x20 grid. Both the provided code and student solutions are written in Java. They employ a self-organizing map (SOM), which is a type of neural network that reduces a high-dimensional input space into a lower-dimensional output space. It is trained by means of an unsupervised learning algorithm. They must implement the following: 1. The Self-Organizing Map unsupervised learning algorithm, using a threshold neighborhood function. 2. A means of encoding binary drawings as SOM inputs. 3. A classification algorithm that translates SOM outputs into labels.