Machine Education: Designing semantically ordered and ontologically guided modular neural networks

The literature on machine teaching, machine education, and curriculum design\nfor machines is in its infancy with sparse papers on the topic primarily\nfocusing on data and model engineering factors to improve machine learning. In\nthis paper, we first discuss selected attempts to date on machine teaching and\neducation. We then bring theories and methodologies together from human\neducation to structure and mathematically define the core problems in lesson\ndesign for machine education and the modelling approaches required to support\nthe steps for machine education. Last, but not least, we offer an\nontology-based methodology to guide the development of lesson plans to produce\ntransparent and explainable modular learning machines, including neural\nnetworks.\n