Neural network estimation of LAL/VPC resions of silkmoth using Genetic Algorithm

When a male silk moth senses sexual pheromone of a female partner by using its antenna, it repeats certain series of walking pattern and arrives to the partner. This walking pattern is generated in Lateral Accessory Lobe (LAL) and the ventral protocerebrum (VPC) domain which controls physical exercise. Therefore, in this study, we elucidate the process of this behavior by constructing a neural network model of the LAL domain. Concretely, we build a model that treats some numbers of neurons as one neuron and estimate strength of each connection between 10 neuron representatives of neuron groups with Genetic Algorithm. The estimated network is verified and consided from engineering and biology.