[2L3-OS-6b] [Organized Session] OS-6

[2L3-OS-6b-02] Validation of symbolic inference based on a value driven associative memory

〇Masahiro Miyata¹, Takashi Omori² (1. Graduate School of Engineering, Tamagawa University, 2. College of Engineering, Tamagawa University)

Keywords:Inference, Associative Memory, Value Calculation System, Model

Intuitive inference and logical inference are modeled separately as the two different processes in brain. However, a site for the logical inference has not been found in the brain, and it is necessary to model a process that realizes the logical inference in a distributed neural network. In this study, we propose an integrated model in which the intuitive inference is represented as a search process of in a continuous and distributed associative memory, and is switched to a symbolic inference mode that biases an associative gain when it found values during the intuitive inference search. In this study, we show the computational model of symbolic inference by associative memory, and we verify its practicality by solving a maze task. As a result, we observed the intuitive one can be represented as the Bayesian probabilistic inference, and the symbolic one based on value.