Interestingness indices for building neural networks based on concept lattices

The difficulty of interpreting performance of neural networks is a well-known problem, which is attracting a lot of attention. In particular, neural networks based on concept lattices present a promising direction in this area. Selection of formal concepts for building a neural network has a key effect on the quality of its performance. Criteria for selecting formal concepts can be based on interestingness indices, when concepts with the highest values of a certain index are used to build a neural network. This article studies the influence of the choice of an interestingness index on the neural network performance.