Evolution of connections in SHRUTI networks

Abstract

SHRUTI is a model of how predicate relations can be represented and reasoned upon using a network of spiking neurons, attempting to model the brain’s ability to perform reasoning using as biologically plausible a means as possible. This paper extends the biological plausibility of the SHRUTI model by presenting a genotype representation of connections in a SHRUTI network using indirect encoding and showing that working networks represented in this way can be produced through an evolutionary process. A multi-objective algorithm is used to minimise the error and the number of weight changes that take place as a network learns