Plasticity-Induced Symmetry Relationships Between Adjacent Self-Organizing Topographic Maps

Sylvester, Jared; Reggia, James A.

doi:10.1162/neco.2009.04-08-763

Cited by 4 publications

(3 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Often such systems try to implement cognitive functions by creating neuro-anatomically grounded simulations of multiple cortical regions using brain-inspired neural networks, among which self-organizing maps (SOMs) are . known to be a promising model for cortical regions [19,21,8].…”

Section: Introductionmentioning

confidence: 99%

“…Due to this property, SOMs can effectively cluster and visualize complex data, and have gained much attention across several disciplines [11]. At the same time, SOMs have successfully captured many biological phenomena observed in cortical regions, including the topographical self-organization of somatosensory, visual, and auditory cortices [16,20], the alignment of multiple feature maps [4], the formation of mirror-symmetric maps [21], and related cognitive phenomena [2].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

Self Cite

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%

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

Self Cite

View full text Add to dashboard Cite

show abstract

“…This mapping preserves input topology non-linearly, meaning that nearby output nodes in a trained map are typically sensitive to similar input patterns. SOMs not only are widely used for unsupervised clustering and visualization in a wide range of computational applications [18,25,29,38,49], but are also reminiscent of many aspects of observed phenomena in biological cortical regions [3,8,37,44,45,47].…”

Section: Introductionmentioning

confidence: 99%

A limit-cycle self-organizing map architecture for stable arm control

et al. 2017

View full text Add to dashboard Cite

Inspired by the oscillatory nature of cerebral cortex activity, we recently proposed and studied self-organizing maps (SOMs) based on limit cycle neural activity in an attempt to improve the information efficiency and robustness of conventional single-node, single-pattern representations. Here we explore for the first time the use of limit cycle SOMs to build a neural architecture that controls a robotic arm by solving inverse kinematics in reach-and-hold tasks. This multi-map architecture integrates open-loop and closed-loop controls that learn to self-organize oscillatory neural representations and to harness non-fixed-point neural activity even for fixed-point arm reaching tasks. We show through computer simulations that our architecture generalizes well, achieves accurate, fast, and smooth arm movements, and is robust in the face of arm perturbations, map damage, and variations of internal timing parameters controlling the flow of activity. A robotic implementation is evaluated successfully without further training, demonstrating for the first time that limit cycle maps can control a physical robot arm. We conclude that architectures based on limit cycle maps can be organized to function effectively as neural controllers.

show abstract