✦ LIBER ✦

Early lexical development in a self-organizing neural network

✍ Scribed by Ping Li; Igor Farkas; Brian MacWhinney

Publisher: Elsevier Science
Year: 2004
Tongue: English
Weight: 404 KB
Volume: 17
Category: Article
ISSN: 0893-6080
DOI: 10.1016/j.neunet.2004.07.004

No coin nor oath required. For personal study only.

✦ Synopsis

In this paper we present a self-organizing neural network model of early lexical development called DevLex. The network consists of two self-organizing maps (a growing semantic map and a growing phonological map) that are connected via associative links trained by Hebbian learning. The model captures a number of important phenomena that occur in early lexical acquisition by children, as it allows for the representation of a dynamically changing linguistic environment in language learning. In our simulations, DevLex develops topographically organized representations for linguistic categories over time, models lexical confusion as a function of word density and semantic similarity, and shows age-of-acquisition effects in the course of learning a growing lexicon. These results match up with patterns from empirical research on lexical development, and have significant implications for models of language acquisition based on self-organizing neural networks.

📜 SIMILAR VOLUMES

A self-organizing neural-network-based f

A self-organizing neural-network-based fuzzy system

✍ Yin Wang; Gang Rong 📂 Article 📅 1999 🏛 Elsevier Science 🌐 English ⚖ 716 KB

A neural-network-based fuzzy system (NNFS) is proposed in this paper. It is a self-organizing neural-network which can partition the input spaces in a flexible way, based on the distribution of the training data in order to reduce the number of rules without any loss of modeling accuracy. Associated

Convergence of a self-organizing stochas

Convergence of a self-organizing stochastic neural network

✍ Olivier Francois; Jacques Demongeot; Thierry Herve 📂 Article 📅 1992 🏛 Elsevier Science 🌐 English ⚖ 451 KB

In this paper, we focus on the convergence of a stochastic neural process. In this process, a "physiologically plausible" Hebb's learning rule gives rise to a self-organization phenomenon. Some preliminary results concern the asymptotic behaviour of the nework given that the update of neurons is eit

Self-organized criticality in a model fo

Self-organized criticality in a model for developing neural networks

✍ Benjamin van den Akker; Borja Ibarz; Raoul-Martin Memmesheimer 📂 Article 📅 2011 🏛 BioMed Central 🌐 English ⚖ 133 KB

Skeletonization by a topology-adaptive s

Skeletonization by a topology-adaptive self-organizing neural network

✍ Amitava Datta; S.K. Parui; B.B. Chaudhuri 📂 Article 📅 2001 🏛 Elsevier Science 🌐 English ⚖ 371 KB

A self-organizing neural network model is proposed to generate the skeleton of a pattern. The proposed neural net is topology-adaptive and has a few advantages over other self-organizing models. The model is dynamic in the sense that it grows in size over time. The model is especially designed to pr

Nonstationary lattice quantization by a

Nonstationary lattice quantization by a self-organizing neural network

✍ Giuseppe Martinelli; Lucio Prina Ricotti; Susanna Ragazzini 📂 Article 📅 1990 🏛 Elsevier Science 🌐 English ⚖ 844 KB

The use of a self-organizing neural network as a vector quantizer in the case of a nonstationary lattice is considered. The nonstationarity is handled by expanding the time-dependent parameters of the lattice into a suitable base. Several experimental results are presented concerning the behaviour o

Parts clustering by self-organizing map

Parts clustering by self-organizing map neural network in a fuzzy environment

✍ Ping-Feng Pai; E.S. Lee 📂 Article 📅 2001 🏛 Elsevier Science 🌐 English ⚖ 607 KB

The description of the attributes or characteristics of the individual parts in a featurebased clustering system is frequently vague, and linguistic, fuzzy number or fuzzy coding is ideally suited to represent these attributes. However, due to the vagueness of the description, the resulting fuzzy me