ECHOROB
Echo State Networks for Developing Language Robots
| Coordinatore | UNIVERSITAET HAMBURG
Organization address
address: EDMUND-SIEMERS-ALLEE 1 contact info |
| Nazionalità Coordinatore | Germany [DE] |
| Totale costo | 161˙968 € |
| EC contributo | 161˙968 € |
| Programma | FP7-PEOPLE
Specific programme "People" implementing the Seventh Framework Programme of the European Community for research, technological development and demonstration activities (2007 to 2013) |
| Code Call | FP7-PEOPLE-2013-IEF |
| Funding Scheme | MC-IEF |
| Anno di inizio | 2015 |
| Periodo (anno-mese-giorno) | 2015-03-01 - 2017-02-28 |
Partecipanti
| # | ||||
|---|---|---|---|---|
| 1 |
UNIVERSITAET HAMBURG
Organization address
address: EDMUND-SIEMERS-ALLEE 1 contact info |
DE (HAMBURG) | coordinator | 161˙968.80 |
Mappa
Word cloud
Esplora la "nuvola delle parole (Word Cloud) per avere un'idea di massima del progetto.
Obiettivo del progetto (Objective)
'In this project, we propose to build a biologically plausible model of sentence comprehension based on recurrent neural networks called reservoirs. Human sentence comprehension is mainly handled by prefrontal cortex areas, which have highly recurrent connectivity. In both biological and artificial neural networks this recurrence is supposed to enable the management of different aspects of time such as working memory and contextual information processing. Here, we propose to develop the Reservoir Computing (RC) paradigm – in particular Echo State Networks (ESN) with incremental learning – to model language comprehension at the sentence level given sequential inputs of words or phonemes. Based on our initial research, a model processing syntactic sentence structures was able to demonstrate generalisation and online prediction capabilities while processing sequential input. For less frequent inputs, the model provided potential explanation for human electrophysiological data. Building on this research, a new model is proposed with the following objectives: (1) processing of all semantic information enabling contextual processing and richer representation of meaning, (2) implementing incremental learning with noisy supervision enabling realistic developmental language acquisition from simple to complex sentences, (3) demonstrating that the model can learn from naïve user’s utterances in several languages, and (4) demonstrating the ability of this model when embodied in a robot to acquire extended language capabilities through human-robot interaction accounting for developmental schemes.'