Self-organized formation of topologically correct feature maps

By Teuvo Kohonen. 2004

8,325 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Cognitive Neuroscience, Electrical and Electronic Engineering

How researchers see this paper

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

In Artificial Intelligence

In Cognitive Neuroscience

In Electrical and Electronic Engineering

Citations in the corpus

Continual Lifelong Learning with Neural Networks: A Review (2018, background): “Thismodelwas shown tooutperformnonincremental denoising autoencoders in classification tasks with theMNIST (LeCun et al., 1998) and the CIFAR-10 (Krizhevsky, 2009) datasets.”
Deep learning in neural networks: An overview (2014, neutral): “…& Mitchison, 1989; Barrow, 1987; Deco & Parra, 1997; Field, 1987; Földiák, 1990; Földiák & Young, 1995; Grossberg, 1976a, 1976b; Hebb, 1949; Kohonen, 1972, 1982, 1988; Kosko, 1990; Martinetz, Ritter, & Schulten, 1990; Miller, 1994; Mozer, 1991; Oja, 1989; Palm, 1992; Pearlmutter &Hinton,…”
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,…”
Cosine Normalization: Using Cosine Similarity Instead of Dot Product in Neural Networks (2017, methodology): “The training of these networks is not using back propagation, and it is hard to build end-to-end deep networks using RBF or SOM.”
Emergence of multimodal action representations from neural network self-organization (2017, background): “…self-organization have been proposed to resemble the dynamics of basic biological findings on Hebbian-like learning and map plasticity (e.g., Fritzke, 1995; Kohonen, 1988). ultimodal action representations from neural network self-orga016/j.cogsys.2016.08.002 .. AWLHierarchical visual processing .”
Open-Ended Learning Leads to Generally Capable Agents (2021, methodology): “We utilise Kohonen Networks (also known as Self-Organising Maps) (Kohonen, 1982) to investigate the high dimensional representations learned by our agents.”
Machine Learning in Aerodynamic Shape Optimization (2022, background): “Self-organizing Maps A SOM is unsupervised learning intended to find low-dimensional representations that preserve the topology of the high-dimensional input space [275].”
A Survey of Artificial Cognitive Systems: Implications for the Autonomous Development of Mental Capabilities in Computational Agents (2007, methodology): “During this period, two alternative connectionist models were being put forward in, for example, Grossberg's Adaptive Resonance Theory (ART) [71] and Kohonen's self-organizing maps (SOMs) [72], often referred to simply as Kohonen networks .”
Clustering: A neural network approach (2010, neutral): “Unlike the SOM (Kohonen, 1982), the Hopfield network (Hopfield, 1982), and the neocognitron (Fukushima, 1980), the ART 1 can deal with arbitrary combinations of binary input patterns.”
Pattern analysis for machine olfaction: a review (2002, background): “Self-organizing maps (SOMs) are connectionist techniques capable of generating topology-preserving clusterings [85].”
Communication with spatially modulated light through turbulent air across Vienna (2014, methodology): “To analyze the intensity structure of the received modes, we use a standard adaptive pattern recognition algorithm in the form of an artificial neural network [39, 40].”
Inference in artificial intelligence with deep optics and photonics (2020, neutral): “…perceptron Rosenblatt, 1957 16 Adaptive switching circuits Widrow & Hoff, 1960 18 The Hopfield network Hopfield, 1982 19 Self-organized feature maps Kohonen, 1982 21 Multi-layer perceptron with backpropagation Selected key milestones and publications are shown, with an emphasis on recent…”
A symbolic-connectionist theory of relational inference and generalization. (2003, background): “…(Rumelhart, Hinton & Williams, 1986), in which exquisitely-detailed error correction by an external teacher driver drives learning, nor fully unsupervised (e.g., Kohonen, 1982; Marshall, 1995; von der Malsburg, 1973), in which learning is driven exclusively by the statistics of the input patterns.”
A Simple Rule for Dendritic Spine and Axonal Bouton Formation Can Account for Cortical Reorganization after Focal Retinal Lesions (2013, result): “Our model stands in contrast to the Kohonen model for selforganizing maps [89,90], traditionally applied to explain cortical remapping.”
Classifier ensembles: Select real-world applications (2008, background): “In general however, there can be many different clusterings for the same data, depending on the clustering algorithm used [22,58,62].”
Towards Deep Developmental Learning (2016, methodology): “Most of these algorithms [91] are variants of the k-means [92], hierarchical clustering [93] or Kohonen-like networks [94].”
Mechanisms for Stable, Robust, and Adaptive Development of Orientation Maps in the Primary Visual Cortex (2013, methodology): “…that captures the essential features of previous incremental Hebbian self-organizing network models for map development (von der Malsburg, 1973; Kohonen, 1982; Obermayer et al., 1990; Sirosh and Miikkulainen, 1994; Barrow et al., 1996; Burger and Lang, 1999, 2001; Bednar and Miikkulainen,…”