#### Filter Results:

#### Publication Year

1992

2001

#### Publication Type

#### Co-author

#### Key Phrase

#### Publication Venue

Learn More

An incremental network model is introduced which is able to learn the important topological relations in a given set of input vectors by means of a simple Hebb-like learning rule. In contrast to previous approaches like the "neural gas" method of Martinetz and Schulten (1991, 1994), this model has no parameters which change over time and is able to continue… (More)

We present a new self-organizing neural network model having two variants. The rst variant performs unsupervised learning and can be used for data visualization, clustering, and vector quantization. The main advantage over existing approaches, e.g., the Kohonen feature map, is the ability of the model to automatically nd a suitable network structure and… (More)

A new on-line criterion for identifying useless" neurons of a self-organizing network is proposed. When this criterion is used in the context of the formerly developed growing neural gas model to guide deletions of units, the resulting method is able to closely track non-stationary distributions. Slow c hanges of the distribution are handled by adaptation… (More)

The reasons to use growing self-organizing networks are investigated. First an overview of several models of this kind is given are they are related to other approaches. Then two examples are presented to illustrate the speciic properties and advantages of incremental networks. In each case a non-incremental model is used for comparison purposes. The rst… (More)

We present a novel self-organizing network which is generated by a growth process. The application range of the model is the same as for Kohonen's feature map: generation of topology-preserving and dimensionality-reducing mappings, e.g., for the purpose of data visualization. The network structure is a rectangular grid which, however, increases its size… (More)

We present a new algorithm for the construction of radial basis function (RBF) networks. The method uses accumulated error information to determine where to insert new units. The diameter of the localized units is chosen based on the mutual distances of the units. To have the distance information always available, it is held up-to-date by a Hebbian learning… (More)

A new vector quantization method { denoted LBG-U { is presented which is closely related to a particular class of neural network models (growing self-organizing networks). LBG-U consists mainly of repeated runs of the well-known LBG algorithm. Each time LBG has converged, however, a novel measure of utility is assigned to each codebook vector. Thereafter,… (More)

A performance comparison of two self-organizing networks, the Ko-honen Feature Map and the recently proposed Growing Cell Structures is made. For this purpose several performance criteria for self-organizing networks are proposed and motivated. The models are tested with three example problems of increasing diiculty. The Kohonen Feature Map demonstrates… (More)

- Kazunori Okada, John W. Powell, Irving Biederman, Gerard Medioni, Kiyoshi Minemura, Hirofumi Saito +33 others
- 2001

We present a new incremental radial basis function network suitable for classiication and regression problems. Center positions are continuously updated through soft competitive learning. The width of the radial basis functions is derived from the distance to topological neighbors. During the training the observed error is accumulated locally and used to… (More)