Self-organizing semantic maps

By Helge J. Ritter, Teuvo Kohonen. 1989

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Deep learning in neural networks: An overview (2014, background): “…1972, 1982, 1988; Kosko, 1990; Martinetz, Ritter, & Schulten, 1990; Miller, 1994; Mozer, 1991; Oja, 1989; Palm, 1992; Pearlmutter &Hinton, 1986; Ritter & Kohonen, 1989; Rubner & Schulten, 1990; Sanger, 1989; Saund, 1994; von der Malsburg, 1973; Watanabe, 1985; Willshaw & von der Malsburg,…”
WordICA—emergence of linguistic representations for words by independent component analysis (2010, methodology): “His method produces one POS tag per word from a predeﬁned tag set (which very much resembles the approach taken in Ritter and Kohonen 1989; Honkela Pulkki and Kohonen 1995 using the self-organizing map as the clustering algorithm).”
Using Conceptors to Manage Neural Long-Term Memories for Temporal Patterns (2017, background): “None of the above examples of dynamical pattern memories has this characteristic, but a diversity of neural learning systems for static patterns have been proposed that have an exploitable internal organization of some sort, for instance self-organizing semantic maps (Ritter and Kohonen, 1989), conn”
Generalizing self-organizing map for categorical data (2006, background): “A sophisticated transformation scheme that integrates similarity information between categorical values into numeric codes is possible to reflect the relationship of categorical data, for example, the one of the topological mappings of animals in [23], in which each animal is attributed with 13…”
Early lexical development in a self-organizing neural network (2004, methodology): “If we denote the Euclidean norm in k-dimensional space as jj$jj k , then it can be proven (see Ritter & Kohonen, 1989) that hðkx 0 K y 0 k 2 D K kx K yk 2 N Þ 2 i% 2 D kx K yk 4 N where h i stands for the average over all possible pairs of vectors x and y.”
Word Representations: A Simple and General Method for Semi-Supervised Learning (2010, background): “The self-organizing semantic map (Ritter & Kohonen, 1989) is a distributional technique that maps words to two dimensions, such that syntactically and semantically related words are nearby (Honkela et al., 1995; Honkela, 1997).”
A Survey of Dimension Reduction Techniques (2002, methodology): “The method of random projections is a simple yet powerful dimension reduction technique that uses random projection matrices to project the data into lower dimensional spaces [47, 32, 33, 35].”
Essentials of the self-organizing map (2013, background): “Kaski (1998) of our group found out that a certain random projection , as introduced in Ritter and Kohonen (1989), of the word histograms is essentially as effective, but is computationally very much lighter.”
Strong systematicity through sensorimotor conceptual grounding: an unsupervised, developmental approach to connectionist sentence processing (2012, methodology): “The SOM architecture has been applied to a diverse set of phenomena, including grammatical and semantic feature classiﬁcation (Ritter and Kohonen 1989; Howell et al. 2005), acquiring phonetic categories (Behnke and Whittenburg 1996), and visual contour integration (Choe and Miikkulainen 2004).”
Rice disease identification using pattern recognition techniques (2008, background): “In the paper, the diseased rice images are classified using SOM neural network where train images are obtained by extracting features of the infected parts of the leave while four different types of images are applied for testing purposes.”