Integrating Language and Cognition: A Cognitive Robotics Approach

Cangelosi, Angelo; Tikhanoff, Vadim; Fontanari, José F.; Hourdakis, Emmanouil

doi:10.1109/mci.2007.385366

Cited by 39 publications

(16 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this way we can assign different weights to the components of the inputs. (8) given by Sek =3 e =1,2 and all k. This is the same effect reported in [44] in which once the inputs are classified into different categories (because of the linguistic component) small differences in the other entries are enhanced, producing a better discrimination of the non -linguistic features. Of course, since there is really no ambiguity in the triplet representation of the inputs, the word-biased NMF mechanism lumps into a single model (say k = 1) all triplets whose third component takes on the value 1, into model k = 2 the triplets whose third component is 2, and so on.…”

Section: A Object-word Input Representationsupporting

confidence: 67%

“…The current predominant view, at least among linguists, is that language and thought are distinct abilities of the mind [4] and a quick comparison between the cognitive and linguistic abilities of apes and parrots appears to be a convincing argument for many researchers. In this contribution we carry further the rather ambitious research program of integrating language and cognition within the Neural Modeling Fields Framework (NMF) [5]- [8]. This is a task of enormous breadth that encompasses many unsolved (and, perhaps, unsolvable) problems such as object perception [9]- [11], symbol grounding which addresses the question of how physical signs can be given meaning [12]- [14], and the emergence of a common lexicon in a population of interacting agents [15]- [19].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A cross-situational algorithm for learning a lexicon using Neural modeling fields

Fontanari

Tikhanoff

Cangelosi

et al. 2009

2009 International Joint Conference on Neural Networks

Self Cite

View full text Add to dashboard Cite

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 objectword 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-tonoise 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.

show abstract

Section: A Object-word Input Representationsupporting

confidence: 67%

Section: Introductionmentioning

confidence: 99%

A cross-situational algorithm for learning a lexicon using Neural modeling fields

Fontanari

Tikhanoff

Cangelosi

et al. 2009

2009 International Joint Conference on Neural Networks

Self Cite

View full text Add to dashboard Cite

show abstract

“…As shown in [1], [2], [3], [4], [5] action and language develop in parallel, influence each other, and base themselves on each other. If brought into the world of robotics, the codevelopment of action and language skills might enable the transfer of properties of action knowledge to linguistic representations, and vice versa, thus enabling the synthesis of robots with complex behavioural and cognitive skills [6], [7].…”

Section: Introductionmentioning

confidence: 99%

The Facilitatory Role of Linguistic Instructions on Developing Manipulation Skills

Massera

Tuci

Ferrauto

et al. 2010

IEEE Comput. Intell. Mag.

View full text Add to dashboard Cite

In this paper, we show how a simulated humanoid robot controlled by an artificial neural network can acquire the ability to manipulate spherical objects located over a table by reaching, grasping, and lifting them. The robot controller is developed through an adaptive process in which the free parameters encode the control rules that regulate the fine-grained interaction between the agent and the environment, and the variations of these free parameters are retained or discarded on the basis of their effects at the level of the behaviour exhibited by the agent. The robot develops the sensory-motor coordination required to carry out the task in two different conditions; that is, with or without receiving as input a linguistic instruction that specifies the type of behaviour to be exhibited during the current phase. The obtained results shown that the linguistic instructions facilitate the development of the required behavioural skills.

show abstract

“…In various experiments Cangelosi et al investigated the grounding of symbols in a computational model [5,6,7]. With the hypothesis that language can emerge from embodied interaction within an environment and a simultaneous exposure to words or "symbols", a number of simulations were conducted.…”

Section: Binding and Grounding In Computational Modelsmentioning

confidence: 99%

Analysing the Multiple Timescale Recurrent Neural Network for Embodied Language Understanding

Heinrich

Magg

Wermter

2015

Springer Series in Bio-/Neuroinformatics

View full text Add to dashboard Cite

How the human brain understands natural language and how we can exploit this understanding for building intelligent grounded language systems is open research. Recently, researchers claimed that language is embodied in most -if not all -sensory and sensorimotor modalities and that the brain's architecture favours the emergence of language. In this chapter we investigate the characteristics of such an architecture and propose a model based on the Multiple Timescale Recurrent Neural Network, extended by embodied visual perception, and tested in a real world scenario. We show that such an architecture can learn the meaning of utterances with respect to visual perception and that it can produce verbal utterances that correctly describe previously unknown scenes. In addition we rigorously study the timescale mechanism (also known as hysteresis) and explore the impact of the architectural connectivity in the language acquisition task.

show abstract

Integrating Language and Cognition: A Cognitive Robotics Approach

Cited by 39 publications

References 17 publications

A cross-situational algorithm for learning a lexicon using Neural modeling fields

A cross-situational algorithm for learning a lexicon using Neural modeling fields

The Facilitatory Role of Linguistic Instructions on Developing Manipulation Skills

Analysing the Multiple Timescale Recurrent Neural Network for Embodied Language Understanding

Contact Info

Product

Resources

About