Reconstructing True Wrong Inductions

Jean-Gabriel Ganascia 1
1 ACASA - Agents Cognitifs et Apprentissage Symbolique Automatique
LIP6 - Laboratoire d'Informatique de Paris 6
Abstract : Many pre-scientific and common sense inductions are erroneous. Here are presented attempts to simulate that kind of inductive reasoning. Our hypothesis is that mistaken inductions are not only due to the lack of facts, but also to the poor description of existing facts and to implicit knowledge. We present a few experiments which aim at validating this hypothesis by simulating with machine learning and data mining techniques the way people erect erroneous theories from observations.
Document type :
Conference papers
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-01352569
Contributor : Lip6 Publications <>
Submitted on : Monday, August 8, 2016 - 3:09:41 PM
Last modification on : Thursday, March 21, 2019 - 1:06:09 PM

Identifiers

  • HAL Id : hal-01352569, version 1

Citation

Jean-Gabriel Ganascia. Reconstructing True Wrong Inductions. AAAI Spring Symposium "What Went Wrong and Why Workshop", Mar 2006, Stanford, United States. pp.26-33. ⟨hal-01352569⟩

Share

Metrics

Record views

67