A Metamodel and Framework for Artificial General Intelligence From Theory to Practice

Guardado en:
Bibliografiske detaljer
Udgivet i:arXiv.org (Feb 11, 2021), p. n/a
Hovedforfatter: Latapie, Hugo
Andre forfattere: Kilic, Ozkan, Liu, Gaowen, Yan, Yan, Kompella, Ramana, Wang, Pei, Thorisson, Kristinn R, Lawrence, Adam, Sun, Yuhong, Srinivasa, Jayanth
Udgivet:
Cornell University Library, arXiv.org
Fag:
Online adgang:Citation/Abstract
Full text outside of ProQuest
Tags: Tilføj Tag
Ingen Tags, Vær først til at tagge denne postø!

MARC

LEADER 00000nab a2200000uu 4500
001 2488773307
003 UK-CbPIL
022 |a 2331-8422 
035 |a 2488773307 
045 0 |b d20210211 
100 1 |a Latapie, Hugo 
245 1 |a A Metamodel and Framework for Artificial General Intelligence From Theory to Practice 
260 |b Cornell University Library, arXiv.org  |c Feb 11, 2021 
513 |a Working Paper 
520 3 |a This paper introduces a new metamodel-based knowledge representation that significantly improves autonomous learning and adaptation. While interest in hybrid machine learning / symbolic AI systems leveraging, for example, reasoning and knowledge graphs, is gaining popularity, we find there remains a need for both a clear definition of knowledge and a metamodel to guide the creation and manipulation of knowledge. Some of the benefits of the metamodel we introduce in this paper include a solution to the symbol grounding problem, cumulative learning, and federated learning. We have applied the metamodel to problems ranging from time series analysis, computer vision, and natural language understanding and have found that the metamodel enables a wide variety of learning mechanisms ranging from machine learning, to graph network analysis and learning by reasoning engines to interoperate in a highly synergistic way. Our metamodel-based projects have consistently exhibited unprecedented accuracy, performance, and ability to generalize. This paper is inspired by the state-of-the-art approaches to AGI, recent AGI-aspiring work, the granular computing community, as well as Alfred Korzybski's general semantics. One surprising consequence of the metamodel is that it not only enables a new level of autonomous learning and optimal functioning for machine intelligences, but may also shed light on a path to better understanding how to improve human cognition. 
653 |a Machine learning 
653 |a Semantics 
653 |a Knowledge bases (artificial intelligence) 
653 |a Reasoning 
653 |a Cognition 
653 |a Reasoning programs 
653 |a Computer vision 
653 |a Network analysis 
653 |a Artificial intelligence 
653 |a Natural language (computers) 
653 |a Knowledge representation 
653 |a Metamodels 
653 |a Time series 
700 1 |a Kilic, Ozkan 
700 1 |a Liu, Gaowen 
700 1 |a Yan, Yan 
700 1 |a Kompella, Ramana 
700 1 |a Wang, Pei 
700 1 |a Thorisson, Kristinn R 
700 1 |a Lawrence, Adam 
700 1 |a Sun, Yuhong 
700 1 |a Srinivasa, Jayanth 
773 0 |t arXiv.org  |g (Feb 11, 2021), p. n/a 
786 0 |d ProQuest  |t Engineering Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/2488773307/abstract/embedded/L8HZQI7Z43R0LA5T?source=fedsrch 
856 4 0 |3 Full text outside of ProQuest  |u http://arxiv.org/abs/2102.06112