The Problem of Induction
By G. Harman, Sanjeev R. Kulkarni. 2006
Subfields: Evaluation & Benchmarks
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Evaluation & Benchmarks
- Vincenzo Crupi
- Stephen Clark
- Felix Hill
- Katya Tentori
- James L. McClelland
- Andrew Kyle Lampinen
- Adam Santoro
- Matthew Botvinick
Citations in the corpus
- Environmental drivers of systematicity and generalization in a situated agent (2019, background): “Rather than engage with this thorny philosophical distinction (which touches upon, e.g., the problem of induction (Vickers, 2009)), we simply emphasize that in our experiments there is a categorical difference between the data on which the agent was trained and test stimuli to which they respond.”
- Machine learning \& artificial intelligence in the quantum domain (2017, background): “are, essentially, a mathematical formalization of Hume’s famous problem of induction (Hume, 1739; Vickers, 2016), which deals with the justification of inductive reasoning.”
- Initial validation of the general attitudes towards Artificial Intelligence Scale (2020, unknown): “During the formation of general attitudes, the generalisations that people arrive at may be biased by cognitive heuristics (Sloman & Lagnado, 2005).”
- Emergent Systematic Generalization in a Situated Agent (2019, background): “Rather than engage with this thorny philosophical distinction (which touches upon, e.g., the problem of induction (Vickers, 2009)), we simply emphasize that in our experiments there is a categorical difference between the data on which the agent was trained and test stimuli to which they respond.”
- Probability, confirmation, and the conjunction fallacy (2008, background): “The former results, taken as a whole, are commonly labelled a ‘‘fallacy’’ in the psychological literature on inductive reasoning, on the basis that h1 j¼ h2 (see, for instance, Gentner & Medina, 1998, p. 283; Heit, 2000, p. 574; Sloman & Lagnado, 2005, p. 105).”
- Designing Theory-Driven User-Centric Explainable AI (2019, background): “It is a weak form of inductive reasoning since only one instance is considered instead of many examples [94, 102].”