The society of mind
Knowledge Acquisition Via Incremental Conceptual Clustering
Machine Learning
Towards cortex sized artificial neural systems
Neural Networks
Configural and elemental associations and the memory coherence problem
Journal of Cognitive Neuroscience
| Hi-index | 0.00 |
The author argues that an artificial general intelligence (AGI) system capable of adapting to various domains autonomously must have the ability to develop domain-specific frames within a practical amount of time; however, current AI technologies are insufficient to achieve this. Frames are knowledge representations which consist of sets of variables. In the frame generation procedure, a significant subprocedure, that of frame candidate generation by variable assimilation, has not yet been realized because of the huge hypothesis space. Representations that can express various relationships among variables in the system can assist in developing this subprocedure, but no such representations have heretofore been known. Through intimate collaboration with neuroscientists, the author searched for clues for such representations in the neuroscience field. Then, the author examined neuroscientific research results to conclude the following: (A) hippocampal formation (HCF) is in charge of frame generation, and (B) distribution equivalent groups (DEGs) are the representations used by HCF for expressing variable relationships. (B) is based on two findings on HCF, namely the phase precession phenomenon and configural association theory. The author used binary-variable assumption to estimate that DEGs exhibit sufficient diversity. Having determined the brain region responsible for a critical function necessary to realize AGI and information representation for that function, this paper offers a foundation for further research into the algorithms used in brain. These results can contribute to the realization of an AGI.