Behavior of Analogical Inference w.r.t. Boolean Functions - Archive ouverte HAL Access content directly
Conference Papers Year : 2018

Behavior of Analogical Inference w.r.t. Boolean Functions

(1) , (2) , (2, 3) , (2)
1
2
3

Abstract

It has been observed that a particular form of ana-logical inference, based on analogical proportions, yields competitive results in classification tasks. Using the algebraic normal form of Boolean functions , it has been shown that analogical prediction is always exact iff the labeling function is affine. We point out that affine functions are also meaningful when using another view of analogy. We address the accuracy of analogical inference for arbitrary Boolean functions and show that if a function is ε-close to an affine function, then the probability of making a wrong prediction is upper bounded by 4ε. This result is confirmed by an empirical study showing that the upper bound is tight. It highlights the specificity of analogical inference, also characterized in terms of the Hamming distance.
Fichier principal
Vignette du fichier
CouHugPraRicIJCAI2018WithKP-24mai.pdf (2.81 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02139765 , version 1 (25-05-2019)

Identifiers

  • HAL Id : hal-02139765 , version 1

Cite

Miguel Couceiro, Nicolas Hug, Henri Prade, Gilles Richard. Behavior of Analogical Inference w.r.t. Boolean Functions. IJCAI 2018 - 27th International Joint Conference on Artificial Intelligence, Jul 2018, Stockholm, Sweden. pp.2057--2063. ⟨hal-02139765⟩
61 View
215 Download

Share

Gmail Facebook Twitter LinkedIn More