The self-organizing map

By Teuvo Kohonen. 1990

Subfields: Representation & Self-Supervised Learning, Model Architectures

How researchers see this paper

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

In Representation & Self-Supervised Learning

In Model Architectures

Citations in the corpus

Lifelong learning of human actions with deep neural network self-organization (2017, methodology): “In the SOM (Kohonen, 1990), two training phases are used to achieve a topographic organization resembling the two phases of a critical period: the organization phase in which the network is trained with a high learning rate and large neighborhood size, and the tuning phase in which these parameters…”
Born to Learn: the Inspiration, Progress, and Future of Evolved Plastic Artificial Neural Networks (2017, methodology): “Unsupervised learning is implemented in neural networks with self-Organising Maps (SOM) (Kohonen, 1982, 1990), auto-encoders (Bourlard and Kamp, 1988), restricted Boltzmann machines (RBM) (Hinton and Salakhutdinov, 2006), and Hebbian plasticity (Hebb, 1949; Gerstner and Kistler, 2002a; Cooper,…”
Neural Combinatorial Optimization with Reinforcement Learning (2016, methodology): “Perhaps most pr minent is the invention of Elastic Nets as a means to solve TSP (Durbin, 1987), and the applic tion of Self Organizing Map to TSP (Fort, 1988; Angeniol et al., 1988; Kohonen, 1990).”
A review of clustering techniques and developments (2017, unknown): “SOM is commonly used for vector quantization, feature extraction and data visualization along with clustering analysis.”
A brain-controlled switch for asynchronous control applications (2000, methodology): “2 To improve the speed of classifier, a vector quantization technique, the LVQ3 algorithm [11] (with three codebook vectors per class), was applied to model the data set.”
Invariances and Data Augmentation for Supervised Music Transcription (2017, background): “However, because the layer-two convolutions in this architecture are designed to exploit local topological structure in the channels, we might hope that end-to-end parameter optimization would find a good topological structure for this space, a kind of self-organizing map [21].”
Hybrid and ensemble-based soft computing techniques in bankruptcy prediction: a survey (2010, methodology): “1998), self-organizing maps (Kohonen 1990), curvilinear component analysis (CCA) (Demartines and Herault 1997; Lee et al.”
Lightweight DDoS flooding attack detection using NOX/OpenFlow (2010, methodology): “The intelligent mechanism employed by our method is based on Self Organizing Maps (SOM) [7], an unsupervised artificial neural network trained with features of the traffic flow.”
Sequence learning using the adaptive suffix trie algorithm (2012, methodology): “The Self Organizing Map(SOM)[14] and the Growing Self Organizing Map(GSOM)[15] are unsupervised clustering algorithms which make use of Hebbian Learning.”
Evolving fuzzy neural networks for supervised/unsupervised online knowledge-based learning (2001, methodology): “The SOM [47,48] may not be efficient when applied for unsupervised adaptive learning on new data as SOM assume a fixed structure and a fixed grid of nodes connected in a topological output space that may not be appropriate for the projection of a particular data set.”
A New Statistical Similarity Measure for Change Detection in Multitemporal SAR Images and Its Extension to Multiscale Change Analysis (2007, methodology): “This task could be carried out by visual inspection, but automatic clustering techniques, like for instance the selforganizing map [32], could be used.”
Deep Learning: A Comprehensive Overview on Techniques, Taxonomy, Applications and Research Directions (2021, methodology): “A Self-Organizing Map (SOM) or Kohonen Map [59] is another form of unsupervised learning technique for creating a low-dimensional (usually two-dimensional) representation of a higher-dimensional data set while maintaining the topological structure of the data.”