LANGUAGE AS AN AID TO CATEGORIZATION: A NEURAL NETWORK MODEL OF EARLY LANGUAGE ACQUISITION

@inproceedings{Mirolli2005LANGUAGEAA,
  title={LANGUAGE AS AN AID TO CATEGORIZATION: A NEURAL NETWORK MODEL OF EARLY LANGUAGE ACQUISITION},
  author={Marco Mirolli and Domenico Parisi},
  year={2005}
}
The paper describes a neural network model of early language acquisition with an emphasis on how language positively influences the categories with which the child categorizes reality. Language begins when the two separate networks that are responsible for nonlinguistic sensory-motor mappings and for recognizing and repeating linguistic sounds become connected together at 1 year of age. Language makes more similar the internal representations of different inputs that must be responded to with… 

Figures from this paper

Robots with Language
TLDR
A neural model of language is described according to which the robot's behaviour is controlled by a neural network composed of two sub-networks, one dedicated to the non-linguistic interactions of the robot with the environment and the other one to processing linguistic input and producing linguistic output.
TALKING TO ONESELF AS A SELECTIVE PRESSURE FOR THE EMERGENCE OF LANGUAGE
Selective pressures for the evolutionary emergence of human language tend to be interpreted as social in nature, i.e., for better social communication and coordination. Using a simple neural network
The Emergence of Language: How to Simulate It
TLDR
An evolutionary sequence is proposed according to which bipedalism and the emergence of the hands represent a selective pressure for developing an ability to predict the consequences of one’s actions, and learning by imitating other individuals is applied to learning to imitate their communicative behaviour.
Translation Source — Not for Attribution An embodied grammar of words 1
This paper presents the merits of integrating a science of language and a science of cognition and behavior. The science of language is empirical linguistics as developed by Zellig Harris and his
Labels as Features (Not Names) for Infant Categorization: A Neurocomputational Approach
TLDR
A neurocomputational model of infant visual categorization, based on self-organizing maps, that implements the unsupervised feature-based approach and predicts that early in development, labels need not act as invitations to form categories nor highlight the commonalities between objects, but they may play a more mundane but nevertheless powerful role as additional features that are processed in the same fashion as other features that characterize objects and object categories.
The impact of labels on visual categorisation: A neural network model
TLDR
A computational model of the impact of labels on visual categorisation is proposed based on selforganising maps and predicts that the observed behaviour in infants is due to a transient form of learning that might lead to the emergence of hierarchically organised categorical structure.
Language as a Cognitive Tool
TLDR
It is argued that the use of language as a cognitive tool might have been an early discovery in hominid evolution, and might have played a substantial role in the evolution of language itself.
Neurocomputational Models Capture the Effect of Learned Labels on Infants’ Object and Category Representations
TLDR
Overall, it is shown that the generally accepted link between internal representations and looking times may be more complex than previously thought.
A neurocomputational model of the effect of learned labels on infants' object representations
TLDR
Simulation data support an account in which labels are features of objects, with the same representational status as the objects’ visual and haptic characteristics.
...
...

References

SHOWING 1-10 OF 20 REFERENCES
How Does Lexical Acquisition Begin? A cognitive perspective
TLDR
Possible strategies of speech segmentation for word discovery and various cues that may facilitate the bootstrapping process involved in the learning, including the prosodic, allophonic, phonotactic and distributional cues are discussed in detail.
Words as Invitations to Form Categories: Evidence from 12- to 13-Month-Old Infants
TLDR
The data reveal that a linkage between words and object categories emerges early enough to serve as a guide in infants' efforts to map words to meanings.
How language helps us think
On formal and empirical grounds, the overt form of language cannot be the vehicle that the mind uses for reasoning. Nevertheless, we most frequently experience our thought as "inner speech". It is
The Adaptive Advantage of Symbolic Theft Over Sensorimotor Toil: Grounding Language in Perceptual Categories
TLDR
The picture of natural language and its origins that emerges from this analysis is that of a powerful hybrid symbolic/sensorimotor capacity, infinitely superior to its purely sensorimotor precursors, but still grounded in and dependent on them.
Language Acquisition: Core Readings
Language Acquisition offers, in one convenient reader, work by the most outstanding researchers in each field and is intended as a snapshot of the sort of theory and research taking place in language
The cognitive functions of language
  • P. Carruthers
  • Psychology, Philosophy
    Behavioral and Brain Sciences
  • 2002
TLDR
The idea is proposed that natural language is the medium for non-domain-specific thinking, serving to integrate the outputs of a variety of domain-specific conceptual faculties (or central-cognitive “quasi-modules”).
Language and Thought: Interdisciplinary Themes
1. Introduction: opening up options Peter Carruthers and Jill Boucher Part I: Language, development and evolution 2. Thought before language: the expression of motion events prior to the impact of a
INTERNAL REPRESENTATIONS OF SENSORY INPUT REFLECT THE MOTOR OUTPUT WITH WHICH ORGANISMS RESPOND TO THE INPUT
TLDR
This chapter describes a series of computer simulations using neural networks that tend to support the action-based view of internal representations, that is, that the manner in which organisms internally represent the sensory input reflects the properties of the actions with which the organisms respond to the sensoryinput.
...
...