Voegtlin, T. (2002). Recursive self-organizing maps. Neural Networks 15(8-9):979-992. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
Neural Gas for Sequences - Strickert, Hammer (2003) (Correct)
....has been proposed, a class of which using embeddings into a finite dimensional vector space [9, 12] but for which a standard rectangular lattice or the Euclidean metric is seldom appropriate for matching the possibly complex data topology. Other approaches model sequential data recursively [3, 4, 13, 14, 15], see e.g. 1] for an overview. Unsupervised sequence processors using recurrent connections recursively compare single sequence elements. Automatically, the similarity structure of entire sequences emerges by the integration of the recursive comparison. In contrast to their supervised recurrent ....
....recursive comparison. In contrast to their supervised recurrent networks counterparts, a large variety of unsupervised recurrent selforganizing models exists: the temporal Kohonen map (TKM) the recurrent SOM (RSOM) recursive SOM (RecSOM) and SOM for structured data (SOMSD) to name just a few [3, 4, 14, 15]. It is not clear which model performs best in certain situations, and the principle capacities of those approaches, their similarities and differences are only partially understood. Recently, a general framework has been proposed to cover these models in a unifying notation [5, 6] the models ....
[Article contains additional citation context not shown here]
T. Voegtlin. Recursive self-organizing maps. Neural Networks, 15(8-9):979--991, 2002.
Unsupervised Recursive Sequence Processing - Strickert, Hammer (2003) (Correct)
.... the biologically plausible dynamics of leaky integrators [1, 9] The recursive SOM (recSOM) and the SOM for structured data (SOMSD) are based on a richer representation of the respective time context, the activation profile of the entire map or the index of the most recent winner, respectively [2, 10]. A general framework for these dynamics has been proposed in [3] We will here focus on the compact and flexible representation of time context given by the winning location of the map for the previously presented sequence element as proposed in [2] Since this approach heavily relies on an ....
....response to sequences with entries only 0 and arbitrary length. Furthermore, the maximum length of sequences which can be represented does not depend on the size of the grid, but on the range of w, i.e. the range of sequence entries. The RecSOM uses a more detailed representation of context [10]: each neuron n j has got a weight w j representing the recent sequence entry and a vector c j , N denoting the number of neurons, which represents the contextual map activation of all neurons in the previous time step. Distance d is recursively computed by d RecSOM ( s 1 , s t ) n j ....
[Article contains additional citation context not shown here]
T. Voegtlin. Recursive self-organizing maps. Neur.Netw., 15(8-9):979--991, 2002.
A General Framework for Self-Organizing Structure.. - Hammer, Micheli.. (Correct)
....has been proposed e.g. in [16, 26, 43] Various approaches alternatively enlarge SOM by recurrent dynamics such as leaky integrators or more general recurrent connections which allow the recursive processing of sequences. Examples are the temporal Kohonen map (TKM) 7] the recursive SOM (RecSOM) [45, 46, 47], or the approaches proposed in [9, 24, 25, 31] The SOM for structured data (SOMSD) 17, 18, 41] constitutes a recursive mechanism capable of processing tree structured data and thus also sequences in an unsupervised way. Alternative models for unsupervised time series processing use for example ....
....which yields solutions for optimum weights w i . Apart from sequence recognition tasks, these models have been successfully applied for learning motion directivity sensitive maps as can be found in the visual cortex [10] Recursive SOM The recursive SOM (RecSOM) has been proposed by Voegtlin [45, 47] as a mechanism for sequence prediction which recursively processes the symbols based on the already computed context. Each neuron is equipped with a weight w i 2 R and, additionally, with a context vector c i 2 R which stores an activation profile of the whole map, indicating, in which ....
[Article contains additional citation context not shown here]
T. Voegtlin and P.F. Dominey. Recursive self-organizing maps. In N.Allison, H.Yin, L.Allinson, and J.Slack (eds.), Advances in Self-Organizing Maps, pages 210-215, Springer, 2001. 36
Mathematical Aspects of Neural Networks - Hammer, Villmann (2003) (Correct)
....is discussed in [76] using metric adaptation to minimize the Kullback Leibler divergence between the auxiliary data space and the weight vector density. 4.1. 2 Further VQ schemes Certainly, SOM itself has been generalized to deal with various alternative scenarios such as variants for time series [132, 137, 147] or more general data structure [58] alternative grid topologies [108] An approach to include statistical properties into SOM learning is given by contingency anlysis as studied in detail by Cottrell Letremy in this volume. For an overview of SOM extension as well as applications we refer to ....
T. Voegtlin. Recursive self-organizing maps. Neural Networks, 15(8-9):979991, 2002.
Self-Organizing Maps for Time Series - Barbara Hammer Alessio (Correct)
No context found.
Voegtlin, T. (2002). Recursive self-organizing maps. Neural Networks 15(8-9):979-992.
Contextual Processing of Graphs using - Self-Organizing Maps Markus (Correct)
No context found.
T. Voegtlin. Recursive self-organizing maps. Neural Networks, 15:979--992, 2002.
Unsupervised Clustering of Continuous - Trajectories Of Kinematic (Correct)
No context found.
T. Voegtlin. Recursive self-organizing maps. Neural Networks, 15:979--992, 2002.
Special Issue - Double Quantization Of (Correct)
No context found.
Voegtlin, T. (2002). Recursive self-organizing maps. Neural Networks, 15(8--9), 979--991.
Self-Organizing Neural Networks for Sequence Processing - Strickert (Correct)
No context found.
T. Voegtlin and P. Dominey. Recursive self-organizing maps. Neural Networks, 15(8--9):979-- 991, 2002.
Neural Methods for Non-Standard Data - Hammer, Jain (Correct)
No context found.
T. Voegtlin. Recursive self-organizing maps. Neural Networks 15(8-9):979-992, 2002.
A General Framework for Unsupervised Processing of.. - Hammer, Micheli, al. (2002) (1 citation) (Correct)
No context found.
T. Voegtlin and P.F. Dominey. Recursive self-organizing maps. In N.Allison, H.Yin, L.Allinson, and J.Slack (eds.), Advances in Self-Organizing Maps, pages 210-215, Springer, 2001.
A General Framework for Unsupervised Processing of.. - Hammer, Micheli, al. (2002) (1 citation) (Correct)
No context found.
T. Voegtlin. Recursive self-organizing maps. Neural Networks 15(8-9):979-992, 2002. 36
Mathematical Aspects of Neural Networks - Hammer (2003) (Correct)
No context found.
T. Voegtlin and P.F. Dominey. Recursive self-organizing maps. In N.Allison, H.Yin, L.Allinson, and J.Slack, editors, Advances in Self-Organizing Maps, pages 210--215, Springer, 2001.
Neural Gas for Sequences - Marc Strickert And (2003) (Correct)
No context found.
T. Voegtlin. Recursive self-organizing maps. Neural Networks, 15(8-9):979--991, 2002.
Self-Organizing Context Learning - Strickert, Hammer (2004) (Correct)
No context found.
T. Voegtlin. Recursive self-organizing maps. Neural Networks, 15(8-9):979--991, 2002.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC