Chrome Extension
WeChat Mini Program
Use on ChatGLM

Keraia: A Knowledge Engineering and Reference AI Architecture

Stephen Richard Varey,Alessandro Di Stefano,The Anh Han

PROCEEDINGS OF NINTH INTERNATIONAL CONGRESS ON INFORMATION AND COMMUNICATION TECHNOLOGY, ICICT 2024, VOL 4(2024)

Teesside Univ

Cited 0|Views1
Abstract
The original intent of artificial intelligence was unveiled at the Dartmouth AI Summer Research Project in 1956. During a 2-month study, it was conjectured that every aspect of learning or any other feature of intelligence could in principle be so precisely described that a machine could be made to simulate it. The question asked then was how one could make machines use language, form abstractions and concepts, and solve the kinds of problems now reserved for humans. The question remains relevant today. This paper presents a reference AI architecture, dubbed Keraia, a symbolic knowledge engineering platform that implements the original intent. The platform includes a repository that serves three purposes: (1) a repository for captured human expertise; (2) an execution platform where previous solutions to known problems can be reused and applied to exact or similar problems; and (3) a collaboration platform where a society of domain experts can create new solutions or modify previous solutions. In support of these objectives, four core features-a novel knowledge representation language, a reference architecture, a general-purpose paradigm builder and a knowledge engineering methodology were developed. The target is to provide domain experts with tools to model precisely how they see their world and how they solve problems. As a case study, we adopt an implementation of the risk board game. It requires expertise and, in these knowledge-rich environments, we introduce a practical knowledge acquisition process and a platform supporting that process.
More
Translated text
Key words
Knowledge engineering,AI architecture,Knowledge representation language,Artificial intelligence
求助PDF
上传PDF
Bibtex
AI Read Science
AI Summary
AI Summary is the key point extracted automatically understanding the full text of the paper, including the background, methods, results, conclusions, icons and other key content, so that you can get the outline of the paper at a glance.
Example
Background
Key content
Introduction
Methods
Results
Related work
Fund
Key content
  • Pretraining has recently greatly promoted the development of natural language processing (NLP)
  • We show that M6 outperforms the baselines in multimodal downstream tasks, and the large M6 with 10 parameters can reach a better performance
  • We propose a method called M6 that is able to process information of multiple modalities and perform both single-modal and cross-modal understanding and generation
  • The model is scaled to large model with 10 billion parameters with sophisticated deployment, and the 10 -parameter M6-large is the largest pretrained model in Chinese
  • Experimental results show that our proposed M6 outperforms the baseline in a number of downstream tasks concerning both single modality and multiple modalities We will continue the pretraining of extremely large models by increasing data to explore the limit of its performance
Upload PDF to Generate Summary
Must-Reading Tree
Example
Generate MRT to find the research sequence of this paper
Data Disclaimer
The page data are from open Internet sources, cooperative publishers and automatic analysis results through AI technology. We do not make any commitments and guarantees for the validity, accuracy, correctness, reliability, completeness and timeliness of the page data. If you have any questions, please contact us by email: report@aminer.cn
Chat Paper

要点】:本文提出了一种名为Keraia的参考AI架构,该架构是一种符号知识工程平台,旨在实现人工智能的原始意图,通过创新的知识表示语言、参考架构、通用范式构建器和知识工程方法论,为领域专家提供精确模拟其世界观和问题解决方式的工具。

方法】:研究团队开发了四种核心功能,包括一种新颖的知识表示语言、一个参考架构、一个通用范式构建器和一个知识工程方法论,以支持领域专家构建精确的模型。

实验】:文章以风险棋盘游戏的实现为案例研究,通过一个实际的知识获取过程和支撑该过程的平台,展示了Keraia架构的实用性。具体数据集名称和实验结果未在摘要中提及。