Showing papers by "Teuvo Kohonen published in 1997"
09 Jun 1997
TL;DR: A data organization system and genuine content-addressable memory called the WEBSOM, a two-layer self-organizing map (SOM) architecture where documents become mapped as points on the upper map, in a geometric order that describes the similarity of their contents.
Abstract: This paper describes a data organization system and genuine content-addressable memory called the WEBSOM. It is a two-layer self-organizing map (SOM) architecture where documents become mapped as points on the upper map, in a geometric order that describes the similarity of their contents. By standard browsing tools one can select from the map subsets of documents that are most similar mutually. It is also possible to submit free-form queries about the wanted documents whereby the WEBSOM locates the best-matching documents. The document map exemplified in this paper has over 100000 map nodes, with 315 inputs at each, and over 1000000 documents have been organized by it. The system has been implemented by software on a general-purpose computer.
212 citations
TL;DR: The adaptive-subspace self-organizing map (ASSOM) is a modular neural network architecture, the modules of which learn to identify input patterns subject to some simple transformations.
Abstract: The adaptive-subspace self-organizing map (ASSOM) is a modular neural network architecture, the modules of which learn to identify input patterns subject to some simple transformations. The learnin...
156 citations
01 Jan 1997
TL;DR: SOM and LVQ algorithms for symbol strings have been introduced and applied to isolatedword recognition, for the construction of an optimal pronunciation dictionary for a given speech recognizer.
Abstract: SOM and LVQ algorithms for symbol strings have been introduced and applied to isolatedword recognition, for the construction of an optimal pronunciation dictionary for a given speech recognizer.
35 citations
01 Jan 1997
33 citations
01 Jan 1997
TL;DR: Two different motives are discernible in neural modeling: an attempt to describe biophysical phenomena that take place in real biological neurons, and a direct attempt to develop new devices based on heuris-tically conceived, although biologically inspired simple components such as threshold-logic units or formal neurons.
Abstract: Two different motives are discernible in neural modeling. The original one is an attempt to describe biophysical phenomena that take place in real biological neurons, whereby it may be expected that some primitives or basic elements of information processing by the brain could be isolated and identified. Another one is a direct attempt to develop new devices based on heuris-tically conceived, although biologically inspired simple components such as threshold-logic units or formal neurons. The circuits thereby designed are usually called artificial neural networks (ANNs).
1 citations