A GCSE maths tutoring game using neural networks
William Lawrence, Jenny Carter, Samad Ahmadi · 2010
This paper investigates the use of neural networks to provide a challenging environment to motivate students of mathematics in further investigation of mathematical concepts. The research focuses on areas of shape, but similar methods could be used for a variety of mathematical topics. The paper presents a game in which a back-propagation neural network is trained by the player to compare areas of mathematical shapes. The original prototype in MATLAB is presented. A demonstration of the idea of a neural network as a opponent using the Python Programming Language further expands on this original work. The results show that a neural network can be used in a variety of ways to support students of differing levels of ability.