Kazunari OZASA, Masashi AONO, Mizuo MAEDA and Masahiko HARA
Abstract. In order to develop an adaptive computing system, we investigate microscopic optical feedback to a group of microbes (Euglena gracilis in this study) with a neural network algorithm, expecting that the unique characteristics of microbes, especially their strategies to survive/adapt against unfavorable environmental stimuli, will explicitly determine the temporal evolution of the microbe-based feedback system. The photophobic reactions of Euglena are extracted from experiments, and built in the Monte-Carlo simulation of a microbe-based neurocomputing. The simulation revealed a high performance of Euglena-based neurocomputing. Dynamic transition among the solution is discussed from the viewpoint of feedback instability. Simulation of Euglena-based neural network computing has been performed with incorporating the photophobic reactions of Euglena experimentally observed. The simulation revealed that Euglena-based neurocomputing can be achieved by taking branch momentums as the variables in the modified Hopfield-Tank model. Global/local feedback instability takes place occasionally in the simulation, which contributes to multiple-solution-search capability. This research has proved that a group of Euglena is one of the suitable biomaterials for microbe-based neural network computing.