Hammer, B., Micheli, A., and Sperduti, A. (2002). A general framework for unsupervised processing of structured data. In M.Verleysen (ed.), European Symposium on Artificial Neural Networks, pages 389-394, D-side publications. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
Self-Organizing Maps for Time Series - Barbara Hammer Alessio Self-citation (Hammer Micheli Sperduti) (Correct)
No context found.
Hammer, B., Micheli, A., and Sperduti, A. (2002). A general framework for unsupervised processing of structured data. In M.Verleysen (ed.), European Symposium on Artificial Neural Networks, pages 389-394, D-side publications.
Self-Organizing Maps for Time Series - Barbara Hammer Alessio Self-citation (Hammer Micheli Sperduti Strickert) (Correct)
No context found.
Hammer, B., Micheli, A., Sperduti, A., and Strickert, M. (2004). A general framework for unsupervised processing of structured data. Neurocomputing 57, 3-35.
Self-Organizing Neural Networks for Sequence Processing - Strickert Self-citation (Hammer Strickert) (Correct)
No context found.
B. Hammer, A. Micheli, A. Sperduti, and M. Strickert. A general framework for unsupervised processing of structured data. Neurocomputing, 57:3--35, 2004.
Neural Methods for Non-Standard Data - Hammer, Jain Self-citation (Hammer) (Correct)
No context found.
B. Hammer, A. Micheli, A. Sperduti, and M. Strickert. A general framework for unsupervised processing of structured data. To appear in Neurocomputing.
Mathematical Aspects of Neural Networks - Hammer (2003) Self-citation (Hammer) (Correct)
No context found.
B. Hammer, A. Micheli, A. Sperduti. A general framework for unsupervised processing of structured data. in: M.Verleysen, editor, ESANN'02, D-side publications, 389--394, 2002.
Mathematical Aspects of Neural Networks - Hammer (2003) Self-citation (Hammer) (Correct)
No context found.
B. Hammer, A. Micheli, M. Strickert, A. Sperduti. A general framework for unsupervised processing of structured data. To appear in: Neurocomputing.
Neural Gas for Sequences - Marc Strickert And (2003) Self-citation (Hammer Strickert) (Correct)
No context found.
B. Hammer, M. Strickert, A. Micheli, and A. Sperduti. A general framework for unsupervised processing of structured data. Neurocomputing, to appear.
Neural Gas for Sequences - Strickert, Hammer (2003) Self-citation (Hammer Strickert) (Correct)
....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 obey the same recursive dynamics, but they differ in their way of internally representing the temporal context. Hence, a crucial point for understanding the models originates from the question about the representational capabilities and the encoding of sequences by the respective ....
....capabilities and the encoding of sequences by the respective temporal context. Important theoretical aspects, such as the dynamics of training, the resulting metric structure, and the notion of topology preservation can be investigated within the scope of that question. First steps can be found in [5, 6]. Here, we will consider the capacity of several context models for representing various types of sequences. Just to mention it, the more elaborate the context models, the better the dealing with complex sequences. The capacity of simple models like TKM is restricted to short sequences over a ....
B. Hammer, M. Strickert, A. Micheli, and A. Sperduti. A general framework for unsupervised processing of structured data. Neurocomputing, to appear.
Unsupervised Recursive Sequence Processing - Strickert, Hammer (2003) Self-citation (Hammer) (Correct)
.... 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 adequate grid topology, we extend this approach to general, possibly ....
....is 1. current symbol is coded by the winning neuron weight, the previous symbol is represented by the linear combination of the winner s context triangle neurons weights. The obtained pairs are clearly expressed in the trained map and only few neurons contain values in an indeterminate interval [ 3 , 3 ]. Results for the reconstruction of three automata can be found in table 1. The left column indicates the number of expressed neurons and the total number of neurons in the map. Note that the automata can be well re obtained from the maps. Reber Grammar: In a third experiment we have used more ....
B. Hammer, A. Micheli, and A. Sperduti. A general framework for unsupervised processing of structured data. In M. Verleysen, editor, European Symposium on Artificial Neural Networks'2002.
A General Framework for Self-Organizing Structure.. - Hammer, Micheli.. Self-citation (Hammer Micheli Sperduti) (Correct)
....We will propose a general framework which transfers the idea of recursive processing of complex data for supervised recurrent and recursive networks to the unsupervised scenario. This general framework covers TKM, RecSOM, SOMSD, and the standard SOM as has already been shown in a short version in [20]. The methods share the basic recursive dynamic but they differ in the way in which structures are internally represented by the neural map. An appropriate choice of the form of internal representations allows to recover the respective mechanism. Moreover, the dynamic of supervised recurrent and ....
B. Hammer, A. Micheli, and A. Sperduti. A general framework for unsupervised processing of structured data. IN M.Verleysen (ed.), European Symposium on Artificial Neural Networks, pages 389-394, D-side publications, 2002.
Dimensions of Neural-symbolic Integration - A Structured Survey - Bader, Hitzler (Correct)
No context found.
B. Hammer, A. Micheli, M. Strickert and A. Sperduti. A general framework for unsupervised processing of structured data. Neurocomputing, 57:3--35, 2004.
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