Go to:
Logótipo
You are here: Start > Publications > View > Building symbolic representations of intuitive real-time skills from performance data
Acesso à coleção completa de ebooks da Knovel
Publication

Building symbolic representations of intuitive real-time skills from performance data

Title
Building symbolic representations of intuitive real-time skills from performance data
Type
Chapter or Part of a Book
Year
1994
Authors
D. Michie
(Author)
Other
The person does not belong to the institution. The person does not belong to the institution. The person does not belong to the institution. Without AUTHENTICUS Without ORCID
R. Camacho
(Author)
FEUP
View Personal Page You do not have permissions to view the institutional email. Search for Participant Publications View Authenticus page View ORCID page
Scientific classification
FOS: Natural sciences > Computer and information sciences
CORDIS: Technological sciences > Technology > Computer technology > Software technology
Other information
Abstract (EN): Real-time control skills are ordinarily tacit - their possessors cannot explicitly communicate them. But given sucient sampling of a trained expert's input-output behaviour, machine learning programs have been found capable of constructing rules which, when run as programs, deliver behaviours similar to those of the original exemplars. These 'clones' are in ef ect symbolic representations of subcognitive behaviours. After validation on simple pole-balancing tasks, the principles have been successfully generalized in flight-simulator experiments, both by Sammut and others at UNSW, and by Camacho at the Turing Institute. A flight plan switches control through a sequence of logically concurrent sets of reactive behaviours. Each set can be thought of as a committee of subpilots who are respectively specialized for rudder, elevators, rollers, thrust, etc. The chairman (the flight plan) knows only the mission sequence, and how to recognize the onset of each stage. This treatment is essentially that of the 'blackboard model', augmented by machine learning to extract subpilot behaviours (seventy-two behaviours in Camacho's auto-pilot for a simulated F-16 combat plane). A 'clean-up' e ffect, first noted in the pole-balancing phase of this enquiry, results in auto-pilots which fly the F-16 under tighter control than the human from whom the behavioural records were sampled.
Language: English
Type (Professor's evaluation): Scientific
Contact: Rui Camacho
No. of pages: 33
License type: Click to view license CC BY-NC
Documents
File name Description Size
mi13 Machine Intelligence 13 chapter 15 224.24 KB
Related Publications

Of the same authors

Behavioral cloning : a correction (1995)
Article in International Scientific Journal
Rui Carlos Camacho de Sousa Ferreira da Silva; D. Michie
Building symbolic representations of intuitive real-time skills from performance data (1992)
Article in International Conference Proceedings Book
D. Michie; Rui Ferreira da Silva
An Engineering Model Of Subcognition (1992)
Article in International Conference Proceedings Book
Rui Ferreira da Silva; D. Michie

Of the same scientific areas

Specification-based testing of user interfaces (2003)
Article in International Scientific Journal
Ana C. R. Paiva; João C. P. Faria; Raul F. A. M. Vidal
Reverse Engineering of Framework Design using a Meta-Patterns-based Approach (2005)
Article in International Conference Proceedings Book
Nuno Flores; Ademar Aguiar
Reverse engineered formal models for GUI testing (2008)
Article in International Conference Proceedings Book
Ana C. R. Paiva; Joao C. P. Faria; Pedro M. C. Mendes
Preliminary experiments with EVA - Serious Games virtual fire drill simulator (2013)
Article in International Conference Proceedings Book
José Fernando M. Silva; João Emílio Almeida; António Pereira; Rosaldo J. F. Rossetti; António Leça Coelho
Intelligent farmer agent for multi-agent ecological simulations optimization (2007)
Article in International Conference Proceedings Book
Filipe Cruz; António Pereira; Pedro Valente; Pedro Duarte; Luís Paulo Reis

See all (6)

Recommend this page Top
Copyright 1996-2025 © Faculdade de Engenharia da Universidade do Porto  I Terms and Conditions  I Accessibility  I Index A-Z  I Guest Book
Page generated on: 2025-06-23 at 14:24:13 | Acceptable Use Policy | Data Protection Policy | Complaint Portal