@inproceedings{fdi:010055253,
  title = {{U}sing belief theory to diagnose control knowledge quality},
  author = {{T}aillandier, {P}. and {D}uch{\^e}ne, {C}. and {D}rogoul, {A}lexis},
  editor = {},
  language = {{ENG}},
  abstract = {{B}oth humans and artificial systems frequently use trial and error methods to problem solving. {I}n order to be effective, this type of strategy implies having high quality control knowledge to guide the quest for the optimal solution. {U}nfortunately, this control knowledge is rarely perfect. {M}oreover, in artificial systems-as in humans-self-evaluation of one's own knowledge is often difficult. {Y}et, this self-evaluation can be very useful to manage knowledge and to determine when to revise it. {T}he objective of our work is to propose an automated approach to evaluate the quality of control knowledge in artificial systems based on a specific trial and error strategy, namely the informed tree search strategy. {O}ur revision approach consists in analysing the system's execution logs, and in using the belief theory to evaluate the global quality of the knowledge. {W}e present a real-world industrial application in the form of an experiment using this approach in the domain of cartographic generalisation. {T}hus far, the results of using our app{P}roach have been encouraging},
  keywords = {{INTELLIGENCE} {ARTIFICIELLE} ; {CROYANCE} ; {THEORIE}},
  numero = {},
  pages = {49--56},
  booktitle = {{I}nternational conference on soft computing as transdiciplinary science and technology},
  year = {2009},
  DOI = {10.1109/{RIVF}.2009.5174663},
  URL = {https://www.documentation.ird.fr/hor/fdi:010055253},
}