[11a-W810-1~10] 31.1 Focused Session "AI Electornics"

△ [11a-W810-7] Theoretical basis of artificial neurons by a two-state stochastic transition model

〇Haruna Katayama¹, Toshiyuki Fujii², Noriyuki Hatakenaka¹ (1.Hiroshima Univ., 2.Asahikawa Medical Univ.)

Keywords:artificial neuron, superconducting quantum interference devices (SQUIDs), a two-state stochastic transition model

The theoretical basis of an artificial neuron is studied using a model that is based on the stochastic transition between two states in a double well potential (a two-state stochastic transition model). It is shown that the stochastic transition model generates an energy-defined sigmoid function acting as an activation function in neurons. The model is also applied to circuit neurons using superconducting quantum interference devices (SQUIDs) in artificial neural networks.