Affiliations: [a] Faculty of Engineering, Maebashi Institute of Technology, Maebashi, Gunma 371-0816, Japan | [b] School of Mathematics, Physics and Computing, University of Southern Queensland, Toowoomba 4350, Australia | [c] School of Psychology, Capital Normal University, Beijing 100048, China | [d] Beijing International Collaboration Base on Brain Informatics and Wisdom Services, Beijing University of Technology, Beijing 100124, China
Abstract: The convergence of systems neuroscience and open science arouses great interest in the current brain big data era, highlighting the thinking capability of intelligent agents in handling multi-source knowledge, information and data across various levels of granularity. To realize such thinking-inspired brain computing during a brain investigation process, one of the major challenges is to find a holistic brain map that can model multi-dimensional variables of brain investigations across brain functions, experimental tasks, brain data and analytical methods synthetically. In this paper, we propose a context-enhanced graph learning method to fuse open knowledge from different sources, including: contextual information enrichment, structural knowledge fusion, and holistic graph learning. Such a method can enhance contextual learning of abstract concepts and relational learning between two concepts that have large gap from different dimensions. As a result, an extensible space, namely Thinking Space, is generated to represent holistic variables and their relations in a map, which currently contributes to the field of brain research for systematic brain computing. In the future, the Thinking Space coupled with the rapid development and spread of artificial intelligence generated content will be developed in more scenarios so as to promote global interactions of intelligence in the connected world.
Keywords: Thinking space, brain computing, web intelligence, brain informatics, context enhancement, knowledge fusion, brain map, brain big data