Unlearning in the BCM Learning Rule for Plastic Self-organization in a Multi-modal Architecture

Lefort, Mathieu; Boniface, Yann; Girau, Bernard

doi:10.1007/978-3-642-21735-7_12

Cited by 2 publications

(9 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The sensory layer uses the BCMu learning rule [26] to provide a tabular coding to a stimulus. This means that the sensory activity is function of a distance between the ... current stimulus and a discriminated one 1 .…”

Section: A Overviewmentioning

confidence: 99%

“…Sensory and perceptive layers as well as their coupling were already presented in [25,26]. In this article, we introduce the cortical layer and its incoming multimodal topographic connections.…”

Section: A Overviewmentioning

confidence: 99%

“…This is achieved by using the BCMu learning rule, a modified version of the BCM learning rule that we proposed in [26]. This learning rule has two coupled dynamics that provide its functional properties:…”

Section: B Learningmentioning

confidence: 99%

“…SOMMA defines generic cortical mapsone for each modality -composed of 3-layers cortical columns. Each column learns a discrimination to a stimulus of the input flow with the BCMu learning rule [26]. These discriminations are self-organized in each map thanks to the coupling with neural fields used as a neighborhood function [25].…”

mentioning

confidence: 99%

“…This multimodal influence drives a joint self-organization of maps and multimodal perceptions of stimuli. This work takes place after the design of a self-organizing map [25] and of a modulation mechanism for influencing its self-organization [26] oriented towards a multimodal purpose. In this paper, we introduce a way to connect these self-organizing maps to obtain a multimap multimodal processing, completing our previous work.…”

mentioning

confidence: 99%

See 4 more Smart Citations

SOMMA: Cortically inspired paradigms for multimodal processing

Lefort

Boniface

Girau

2013

The 2013 International Joint Conference on Neural Networks (IJCNN)

Self Cite

View full text Add to dashboard Cite

SOMMA (Self Organizing Maps for Multimodal Association) consists on cortically inspired paradigms for multimodal data processing. SOMMA defines generic cortical mapsone for each modality -composed of 3-layers cortical columns. Each column learns a discrimination to a stimulus of the input flow with the BCMu learning rule [26]. These discriminations are self-organized in each map thanks to the coupling with neural fields used as a neighborhood function [25]. Learning and computation in each map is influenced by other modalities thanks to bidirectional topographic connections between all maps. This multimodal influence drives a joint self-organization of maps and multimodal perceptions of stimuli. This work takes place after the design of a self-organizing map [25] and of a modulation mechanism for influencing its self-organization [26] oriented towards a multimodal purpose. In this paper, we introduce a way to connect these self-organizing maps to obtain a multimap multimodal processing, completing our previous work. We also give an overview of the architectural and functional properties of the resulting paradigm SOMMA.

show abstract

Section: A Overviewmentioning

confidence: 99%

Section: A Overviewmentioning

confidence: 99%

Section: B Learningmentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

See 3 more Smart Citations

SOMMA: Cortically inspired paradigms for multimodal processing

Lefort

Boniface

Girau

2013

The 2013 International Joint Conference on Neural Networks (IJCNN)

Self Cite

View full text Add to dashboard Cite

show abstract

Kick-starting concept formation with intrinsically motivated learning: the grounding by competence acquisition hypothesis

Mannella

Tummolini

2022

Phil. Trans. R. Soc. B

View full text Add to dashboard Cite

Although the spontaneous origins of concepts from interaction is often given for granted, how the process can start without a fully developed sensorimotor representation system has not been sufficiently explored. Here, we offer a new hypothesis for a mechanism supporting concept formation while learning to perceive and act intentionally. We specify an architecture in which multi-modal sensory patterns are mapped in the same lower-dimensional representation space. The motor repertoire is also represented in the same space via topological mapping. We posit that the acquisition of these mappings can be mutually constrained by maximizing the convergence between sensory and motor representations during online interaction. This learning signal reflects an intrinsic motivation of competence acquisition. We propose that topological alignment via competence acquisition eventually results in a sensorimotor representation system. To assess the consistency of this hypothesis, we develop a computational model and test it in an object manipulation task. Results show that such an intrinsically motivated learning process can create a cross-modal categorization system with semantic content, which supports perception and intentional action selection, which has the resources to re-enact its own multi-modal experiences, and, on this basis, to kick-start the formation of concepts grounded in the external environment. This article is part of the theme issue ‘Concepts in interaction: social engagement and inner experiences’.

show abstract

Unlearning in the BCM Learning Rule for Plastic Self-organization in a Multi-modal Architecture

Cited by 2 publications

References 14 publications

SOMMA: Cortically inspired paradigms for multimodal processing

SOMMA: Cortically inspired paradigms for multimodal processing

Kick-starting concept formation with intrinsically motivated learning: the grounding by competence acquisition hypothesis

Contact Info

Product

Resources

About