A Framework for Evolving Spiking Neural P Systems
Lovely Joy P. Casauay, Francis George C. Cabarle, Ivan Cedric H. Macababayao, Ren Tristan A. De La Cruz, Henry N. Adorna, Xiangxiang Zeng and Miguel Ángel Martínez-Del-Amor
In the literature for spiking neural P systems (SN P systems) there is a need for further research on their optimization and, consequently, for automating this optimization process. We address this gap by designing a genetic algorithm (GA) framework that transforms an initial SN P system Πinit, designed to approximate a function 𝑓 (𝑤, 𝑥, 𝑦, . . .) = 𝓏, into a smaller or more precise system Πfinal that also approximates the output 𝓏 given the same input/s 𝑤, 𝑥, 𝑦, . . .. The GA framework is constrained to evolve Πinit, only through its topology. The rules inside the neurons must stay constant, while the synapses and neurons may vary. Experiments conducted showed that using GA to evolve the topology of a designed Πinit, decreases the number of its neurons and synapses, and makes it more precise. The GA framework is especially useful on SN P systems containing, as a subgraph of its synapse graph, a smaller SN P system computing 𝑓.
Keywords: Spiking neural P system, P system, spiking neural networks, genetic algorithm, membrane computing, neural computing, evolutionary computing