[1H2-GS-1a] 基礎・理論：人の認知・知覚

[1H2-GS-1a-01] Objectification Learning

To explode the scope of inference

〇Hiroshi Yamakawa^1,2 (1. The University of Tokyo, 2. The Whole Brain Architecture Initiative, a specified non-profit organization)

Keywords: aligned structures, attention in machine learning , verification procedure hypothesis for relation, case index set, binding problem

To greatly explode range of thinking for AI, it needs to be able to autonomously discover new alignment structures that can serve as a framework for inductive reasoning. A study aimed at a method for automatically constructing the three types of relations that support alignment structures was conducted. It was assumed that the specification relationship and their equivalence could be configured in various ways by computational procedures. However, the comparability could only be obtained from the properties of the sensors. Therefore, a method to obtain a new alignment structure by combining various specification relations that match the comparability of sensors was discussed. It can be regarded as "objectification" in the sense that it treats the object as an object that is easy to recognize and operate. And among the deep generative models currently presented, the model with the attention function looks satisfying the realization requirement for learning the object based on the alignment structure. However, learning of objectification itself still seems to be difficult.