Topology conserving mappings for learning motor tasks

Ritter, Helge; Schulten, Klaus

doi:10.1063/1.36242

Cited by 44 publications

(24 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Such models have been successfully used in applications such as speech processing [26], robotics [40,32] and image processing [36]. However, most common approaches are not able to provide good neighborhood and topology preservation if the logical structure of the input patten is not known a priori.…”

Section: Topology Learningmentioning

confidence: 99%

3D reconstruction of medical images from slices automatically landmarked with growing neural models

et al. 2015

View full text Add to dashboard Cite

In this study, we utilise a novel approach to segment out the ventricular system in a series of high resolution T1-weighted MR images. We present a brain ventricles fast reconstruction method. The method is based on the processing of brain sections and establishing a fixed number of landmarks onto those sections to reconstruct the ventricles 3D surface. Automated landmark extraction is accomplished through the use of the self-organising network, the Growing Neural Gas (GNG), which is able to topographically map the low dimensionality of the network to the high dimensionality of the contour manifold without requiring a priori knowledge Email addresses: agelopa@wmin.ac.uk (Anastassia Angelopoulou), psarroa@wmin.ac.uk (Alexandra Psarrou), jgarcia@dtic.ua.es (Jose Garcia-Rodriguez), sorts@dtic.ua.es (Sergio Orts-Escolano), jazorin@dtic.ua.es (Jorge Azorin-Lopez), ken.revett@bue.edu.eg (Kenneth Revett) February 16, 2014 of the input space structure. Moreover, our GNG landmark method is tolerant to noise and eliminates outliers. Our method accelerates the classical surface reconstruction and filtering processes. The proposed method offers higher accuracy compared with methods with similar efficiency as Voxel Grid. Preprint submitted to Neurocomputing

show abstract

Section: Topology Learningmentioning

confidence: 99%

3D reconstruction of medical images from slices automatically landmarked with growing neural models

et al. 2015

View full text Add to dashboard Cite

show abstract

“…In many proposed EKMs (Cameron et al, 1998;Heikkonen and Koikkalainen, 1997;Rao and Fuentes, 1998;Ritter and Schulten, 1986;Smith, 2002;Touzet, 1997;Versino and Gambardella, 1995), each sensory input u is mapped directly to a motor control command c. In such a direct-mapping EKM (Fig. 1A), each neuron i has a sensory weight vector…”

Section: Overviewmentioning

confidence: 99%

“…This paper describes a new feature map approach to learning sensorimotor control called cooperative EKMs with indirect mapping. An indirect-mapping EKM (Low et al, 2002) differs from existing direct-mapping methods (Cameron et al, 1998;Heikkonen and Koikkalainen, 1997;Rao and Fuentes, 1998;Ritter and Schulten, 1986;Smith, 2002;Touzet, 1997;Versino and Gambardella, 1995) in two ways:…”

Section: Introductionmentioning

confidence: 99%

“…The third approach uses a Self-Organizing Feature Map (SOFM) (Kohonen, 2000) such as the Extended Kohonen Map (EKM) (Ritter and Schulten, 1986) that self-organizes to partition the continuous input (or output) space into localized regions. The generalization capability of the feature map arises from its self-organization during training such that each neuron is trained to map a localized sensory region to a desired motor control output.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An Ensemble of Cooperative Extended Kohonen Maps for Complex Robot Motion Tasks

2005

View full text Add to dashboard Cite

Self-organizing feature maps such as Extended Kohonen Maps (EKMs) have been very successful at learning sensorimotor control for mobile robot tasks. This paper presents a new ensemble approach called cooperative EKMs with indirect mapping to achieve complex robot motion. An indirect-mapping EKM self-organizes to map from the sensory input space to the motor control space indirectly via a control parameter space. Quantitative evaluation reveals that indirect mapping can provide finer, smoother, and more efficient motion control than does direct mapping by operating in a continuous, rather than discrete, motor control space. It is also shown to outperform basis function neural networks. Furthermore, training its control parameters with recursive least squares enables faster convergence and better performance compared to gradient descent. The cooperation and competition of multiple self-organized EKMs allow a non-holonomic mobile robot to negotiate unforeseen, concave, closely spaced, and dynamic obstacles. Qualitative and quantitative comparisons with neural network ensembles employing weighted sum reveal that our method can achieve more sophisticated 1 The final version of this article has been published in

show abstract

“…The applications of connectionism to robotics are initiated in the late '80s with the works of Ritter and Schulten [1986;, Kawato et al [1987a], Grossberg [1986], Kuperstein [1988a], … These works consider mainly the control of sensory-motor systems, and more precisely visuo-motor systems, e.g. the visual control of a robotic arm [Ritter & Schulten, 1986;Bullock & Grossberg, 1988;Kuperstein, 1988a], or eye movement control and the formation of invariant maps of these movements [Grossberg & Kuperstein, 1986]… An important problem in robotics is the modeling of the kinematical and dynamical transformations.…”

Section: Sensory-motor Functionalitiesmentioning

confidence: 99%

Modular Neural Architectures for Robotics

Buessler¹,

Urban²

2003

Biologically Inspired Robot Behavior Engineering

View full text Add to dashboard Cite

Abstract:The learning of sensory-motor functions have motivated important research works that emphasize a major demand: the combination of multiple neural networks to implement complex functions. A review of a number of works presents some implementations in robotics, describing the purpose of the modular architecture, its structure, and the learning technique that was applied. The second part of the chapter presents an original approach to this problem of network training, proposed by our group. Based on a bi-directional architecture, multiple networks can be trained online with simple local learning rules, while the robotic systems interact with their environment.

show abstract

Topology conserving mappings for learning motor tasks

Cited by 44 publications

References 0 publications

3D reconstruction of medical images from slices automatically landmarked with growing neural models

3D reconstruction of medical images from slices automatically landmarked with growing neural models

An Ensemble of Cooperative Extended Kohonen Maps for Complex Robot Motion Tasks

Modular Neural Architectures for Robotics

Contact Info

Product

Resources

About