We believe that in many machine learning systems it would be effective to create a pedagogical environment where both the machines and the humans can incrementally learn to solve problems through interaction and adaptation. We are designing an optical music recognition (OMR) workflow system where human operators can intervene to correct and teach the system at certain stages so that they can learn from the errors and the overall performance can be improved progressively as more music scores are

more »

... processed. In order to instantiate this pedagogical process, we have developed a series of browser-based interfaces for the different stages of our OMR workflow: image preprocessing, music symbol recognition, musical notation recognition, and final representation construction. In most of these stages we integrate human input with the aim of teaching the computers to improve the performance.