---
title: "What's in a Deep Model? A Characterization of Knowledge Depth in Intelligent Safety Systems"
authors:
  - "David Klein"
  - "Timothy W. Finin"
doi: ""
url: "https://ijcai.org/proceedings/1987/111"
pdf: "https://ijcai.org/proceedings/1987/0111.pdf"
venue: "Proceedings of the Tenth International Joint Conference on Artificial Intelligence"
year: 1987
pages: "559-561"
track: "Knowledge Representation"
keywords:
---

# What's in a Deep Model? A Characterization of Knowledge Depth in Intelligent Safety Systems

David Klein, Timothy W. Finin

*Proceedings of the Tenth International Joint Conference on Artificial Intelligence*, pages 559-561.

## Abstract

While one can characterize deep and shallow models at a high level of abstraction and contrast their relative merits in a general way, this . provides l!ttle direction for ~o~ledge engineering. In particular, the f1eld lacks a clear defm1t1on of 'knowledge depth' and lacks gu_idelines . . regarding t~e appropriate depth Of modelS ~Or a g1ven application; . rn thiS P.aper we provide a very s1mple operational def1n!~on of knowledge depth' and use it to exam1ne the opportumties for varying depth in intelligent safety sy_stems. The paper illust~ates a domain-independent mode of analysis for examining progressively deeper models of expertise, and sketches some domain-specific guidelines for constructing intelligent safety systems. We draw ur.on examples from the domains of nuclear reactor managemen , chemical plant control, and management of computer installation operations.