Model of multi-modal cortical processing: Coherent learning in self-organizing modules

Ménard, Olivier; Frezza-Buet, Hervé

doi:10.1016/j.neunet.2005.06.036

Cited by 20 publications

(23 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [13], a separate multimodal SOM is used for associating unimodal SOMs, although winning node indexes rather than activity patterns are used as inputs to the multimodal SOM. A more realistic multi-SOM architecture can be found in [15], which is characterized by iterative competition among nodes and topographic connections between SOMs.…”

Section: Introductionmentioning

confidence: 99%

A Self-Organizing Map Architecture for Arm Reaching Based on Limit Cycle Attractors

Huang¹,

Gentili²,

Reggia³

2016

Proceedings of the 9th EAI International Conference on Bio-Inspired Information and Communications Technologies (Formerly BIONE

View full text Add to dashboard Cite

Creating and studying neurocognitive architectures is an active and increasing focus of research efforts. Based on our recent research that uses neural activity limit cycles in selforganizing maps (SOMs) to represent external stimuli, this study explores the use of such limit cycle attractors in a neurocognitive architecture for an open-loop arm reaching task. The goal is to learn to produce a static motor command for arm joints that moves the manipulator to a target spatial location, while the internal neural activity remains oscillatory. Unlike with static SOMs, stabilizing output based on changing neural activity becomes an important issue. Our architecture is also characterized by simple and forgiving timing requirements, meaning that the time of gating among neural components can be set relatively arbitrarily due to the repetitiveness of limit cycle activity. The results indicate that our architecture generalizes to unseen data, and that the overall performance is insensitive to exact gate timing.

show abstract

Section: Introductionmentioning

confidence: 99%

A Self-Organizing Map Architecture for Arm Reaching Based on Limit Cycle Attractors

Huang¹,

Gentili²,

Reggia³

2016

Proceedings of the 9th EAI International Conference on Bio-Inspired Information and Communications Technologies (Formerly BIONE

View full text Add to dashboard Cite

show abstract

“…The predictive term can then be considered as a corticocortical modulation to be contrasted with the thalamic input from the senses, a division that is also found in neural field models of multimodal integration [10]. To remain as simple as possible relatively to the competition between the immediate external stimulation and future-oriented inner projections, α is fixed and a single predictor is considered (see Fig.…”

Section: Proposed Modelmentioning

confidence: 99%

Predictive neural fields for improved tracking and attentional properties

Quinton

Girau

2011

The 2011 International Joint Conference on Neural Networks

View full text Add to dashboard Cite

Abstract-Predictive capabilities are added to the competition mechanism known as the Continuum Neural Field Theory, in order to improve and extend its attentional properties. In order to respect the distributed and bio-inspired nature of the model, the prediction is introduced as an internal stimulation, directly determined by the past field activity. Building on mathematical developments and optimization techniques, performance is ascertained on a 2D tracking application where the system must robustly focus on a target despite rapid movements, noise and distracters. In addition to a consistent gain on previously observed capabilities, the extended model can also track stimuli with full occlusions and static obstacles on the trajectory.

show abstract

“…The proposed architecture is based on bijama model [5] in its dynamics via strip-like connections. The interest of the intermediate architecture is to consider the past of the input stream in current map response.…”

Section: The Architecturementioning

confidence: 99%

“…This is rather difficult as explained in [7]. In bijama model, the evaluation of units activities follows an asynchronous and parallel scheme [5] not detailed here. Evaluation of all the units occurs at discrete time instances which are called time steps.…”

Section: The Architecturementioning

confidence: 99%

Tracking non-stationary dynamical system phase using multi-map and temporal self-organizing architecture

Khouzam

Frezza-Buet

2011

2011 Third World Congress on Nature and Biologically Inspired Computing

View full text Add to dashboard Cite

Abstract-This paper presents a multi-map recurrent neural architecture, exhibiting self-organization to deal with the partial observations of the phase of some dynamical system. The architecture captures the dynamics of the system by building up a representation of its phases, coping with ambiguity when distinct phases provide identical observations. The architecture updates the resulted representation to adapt to changes in its dynamics due to self-organization property. Experiments illustrate the dynamics of the architecture when fulfilling this goal.

show abstract

Model of multi-modal cortical processing: Coherent learning in self-organizing modules

Cited by 20 publications

References 16 publications

A Self-Organizing Map Architecture for Arm Reaching Based on Limit Cycle Attractors

A Self-Organizing Map Architecture for Arm Reaching Based on Limit Cycle Attractors

Predictive neural fields for improved tracking and attentional properties

Tracking non-stationary dynamical system phase using multi-map and temporal self-organizing architecture

Contact Info

Product

Resources

About