Recent years have seen the discovery of gaseous transmitters in
biological nervous systems. An ANN
inspired by such gaseous signalling, the GasNet,
has
previously been shown to be more evolvable than traditional ANNs.
Here we present 2 new versions of the GasNet which take further
inspiration from the properties of gaseous signalling. The plexus
model
is inspired by the cortical nNOS plexus
and the properties of the NO signal it generates. The receptor
model
is inspired by the mediating action of
neurotransmitter receptors. Both models are shown to significantly
further improve evolvability. We describe preliminary results
suggesting that the reasons for the increase in evolvability is the
loose coupling of distinct signalling mechanisms. Issues surrounding
the degree of coupling between these mechanisms, one `chemical' and
one `electrical', are discussed.