Self-Organizing Maps

By Teuvo Kohonen. 1995

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

Continual Lifelong Learning with Neural Networks: A Review (2018, background): “Reported results on CORe50 (Lomonaco & Maltoni, 2017) and iCIFAR-100 (Krizhevsky, 2009) show that AR1 allows the training of deep convolutional models with less forgetting, outperforming LwF, EWC, and SI. Ensemble methods have been proposed to alleviate catastrophic forgetting by training multiple c”
Lifelong Learning of Spatiotemporal Representations With Dual-Memory Recurrent Self-Organization (2018, background): “Different models of neural network self-organization have been proposed that resemble the dynamics of Hebbian learning and plasticity (Fritzke, 1995; Kohonen, 1995; Marsland et al., 2002), with neural map organization resulting from unsupervised statistical learning.”
MatInspector and beyond: promoter analysis based on transcription factor binding sites (2005, methodology): “These feature vectors are then used to generate a standard self-organizing map (Kohonen (1995)).”
Data analysis for electronic nose systems (2006, unknown): “unsupervised learning network [104].”
Learning Forward Models for the Operational Space Control of Redundant Robots (2010, methodology): “Based on self-organising maps (Kohonen, 2001), Martinetz et al (1990b,a); Walter and Schulten (1993) learn a mapping between end eﬀector position measured by two cameras and joint positions on a three degrees of freedom robot.”
Building interpretable fuzzy models for high dimensional data analysis in cancer diagnosis (2011, methodology): “…of features (genes), usually in the range of 2,000-30,000, is much larger than the number of examples (usually in the range of 40-200 40-200 Unsupervised methods, such as Clustering [4], and Self-Organizing Maps (SOMs) [5] were initially used to analyse the relationships among different genes.”
Three learning phases for radial-basis-function networks (2001, unknown): “It is de®ned by h t h t 1 1 s m j p h t : 22 For a detailed treatment on LVQ learning algorithms see Kohonen (1995).”
Applying Data Mining Techniques to e-Learning Problems (2007, background): “In [60, 61], an in-depth study describing the usability of Artificial Neural Networks and, more specifically, of Kohonen’s Self-Organizing Maps (SOM) [43] for the evaluation of students in a tutorial supervisor (TS) system, as well as the ability of a fuzzy TS to adapt question difficulty in the eva”