Learning about Actions and Events in Shared NeMuS

Tenório, M. R., Mota, E. D. S., Howe, J. M. & Garcez, A. S. D. A. (2017). Learning about Actions and Events in Shared NeMuS. CEUR Workshop Proceedings, 2003, ISSN 1613-0073

[img]
Preview
Text - Published Version
Download (172kB) | Preview

Abstract

The categorization process of information from pure data or learned in unsuper- vised artificial neural networks is still manual, especially in the labeling phase. Such a process is fundamental to knowledge representation [6], especially for symbol-based systems like logic, natural language processing and textual infor- mation retrieval. Unfortunately, applying categorization theory in large volumes of data does not lead to good results mainly because there is no generic and systematic way of categorizing such data processed by artificial neural networks and joining investigated conceptual structures. Connectionist approaches are capable of extracting information from arti- ficial neural networks, but categorizing them as symbolic knowledge have been little explored. The obstacle lies on the difficulty to find logical justification from response patterns of these networks [2]. This gets worse when considering induc- tive learning from dynamic data which is very important to Cognitive Sciences that considers categorization as a mental operation of classifying objects, actions and events [1]. We shall address the discoveries of our on-going investigation on the problem of inductively learning (IL) from dynamic data by applying a novel framework for neural-symbolic representation and reasoning called share Neural Multi-Space (NeMuS) used in the Amao system[4]. Instead of woking like traditional ap- proaches for ILP, e.g. [5], Amao uses a shared NeMuS of a give background knowledge (BK) and uses inverse unification as the generalization mechanism of a set of logically connected expressions from the Herbrand Base (HB) of BK that defines positive examples.

Publication Type: Conference or Workshop Item (Paper)
Additional Information: Copyright © 2017 for this paper by its authors. Copying permitted for private and academic purposes. Modification of items is not permitted unless a suitable license is granted by its copyright owners. Copying or use for commercial purposes is forbidden unless an explicit permission is acquired from the copyright owners.
Departments: School of Mathematics, Computer Science & Engineering > Computer Science
URI: http://openaccess.city.ac.uk/id/eprint/18950

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year

View more statistics