Advanced search
Start date
Betweenand


A cross-situational algorithm for learning a lexicon using Neural Modeling Fields

Full text
Author(s):
Fontanari, Jose F. ; Tikhanoff, Vadim ; Cangelosi, Angelo ; Perlovsky, Leonid I. ; IEEE
Total Authors: 5
Document type: Journal article
Source: 2007 IEEE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-6; v. N/A, p. 3-pg., 2009-01-01.
Abstract

Cross-situational learning is based on the idea that a learner can determine the meaning of a word by finding something in common across all observed uses of that word. Although cross-situational learning is usually modeled through stochastic guessing games in which the input data vary erratically with time (or rounds of the game), here we investigate the possibility of applying the deterministic Neural Modeling Fields (NMF) categorization mechanism to infer the correct object-word mapping. Two different representations of the input data were considered. The first is termed object-word representation because it takes as inputs all possible object-word pairs and weighs them by their frequencies of occurrence in the stochastic guessing game. A re-interpretation of the problem within the perspective of learning with noise indicates that the cross-situational scenario produces a too low signal-to-noise ratio, explaining thus the failure of NMF to infer the correct object-word mapping. The second representation, termed context-word, takes as inputs all the objects that are in the pupil's visual field (context) when a word is uttered by the teacher. In this case we show that use of two levels of hierarchy of NMF allows the inference of the correct object-word mapping. (AU)

FAPESP's process: 04/06156-3 - Replicators: applications in pre-biotic evolution and language
Grantee:José Fernando Fontanari
Support Opportunities: Research Projects - Thematic Grants