Self-Organized Formation of Topologically Correct Feature Maps.¶
Kohonen, T. (1982). Self-Organized Formation of Topologically Correct Feature Maps. Biological Cybernetics, 43(1), 59-69.
Cited by¶
5 citations across 5 artifacts.
Each citation links to the sentence it supports in the citing article.
Primes¶
- Hebbian Learning
- Hebb's rule, refined into normalizing and threshold variants, underlies accounts of associative memory and receptive-field formation. Machine learning. Hebbian and competitive rules underlie self-organizing maps, Hopfield networks, sparse coding, and early unsupervised pretraining; normalizing Hebbian rules connect to principal-component extraction.
This sourceIntroduces self-organizing maps — competitive Hebbian learning producing organized structure from input statistics without supervision.
Supported in partVerified against the publisher's abstract
Kohonen's abstract gives an unsupervised, self-organizing process forming topologically correct feature maps, but names no Hebbian or competitive rule.
“a principle has been discovered which facilitates the automatic formation of topologically correct maps of features of observable events.”
- Hebb's rule, refined into normalizing and threshold variants, underlies accounts of associative memory and receptive-field formation. Machine learning. Hebbian and competitive rules underlie self-organizing maps, Hopfield networks, sparse coding, and early unsupervised pretraining; normalizing Hebbian rules connect to principal-component extraction.
- Topographic Map
- In machine learning, Kohonen self-organising maps explicitly optimise neighbourhood preservation from a high-dimensional source onto a 2D substrate, and t-SNE and UMAP embed high-dimensional data with neighbourhood preservation as the objective.
This sourceIntroduces the self-organizing map, optimizing neighbourhood preservation from a high-dimensional source onto a low-dimensional substrate.
Supported in partVerified against the publisher's abstract
Kohonen's 1982 paper abstract describes topological order preservation onto a one- or two-dimensional array, supporting the SOM clause of this sentence but not the t-SNE/UMAP clause.
“the signal representations are automatically mapped onto a set of output responses in such a way that the responses acquire the same topological order as that of the primary events”
- In machine learning, Kohonen self-organising maps explicitly optimise neighbourhood preservation from a high-dimensional source onto a 2D substrate, and t-SNE and UMAP embed high-dimensional data with neighbourhood preservation as the objective.
Domain-specific¶
- Retinotopy
- What genuinely recurs across distinct substrates is the topographic map — a continuous, neighbourhood-preserving mapping from a stimulus manifold onto a representational surface, with non-uniform magnification allocating more substrate to high-importance regions — and this pattern reappears as legitimate co-instances, not metaphors: Kohonen self-organizing maps (1982) and topographic feature maps in artificial neural networks
This sourceKohonen’s self-organizing process, in which signal representations are automatically mapped so that responses acquire the same topological order as the input events, forming topologically correct feature maps.
Supported in partVerified against the work's full text
“a principle has been discovered which facilitates the automatic formation of topologically correct maps of features of observable events”
- What genuinely recurs across distinct substrates is the topographic map — a continuous, neighbourhood-preserving mapping from a stimulus manifold onto a representational surface, with non-uniform magnification allocating more substrate to high-importance regions — and this pattern reappears as legitimate co-instances, not metaphors: Kohonen self-organizing maps (1982) and topographic feature maps in artificial neural networks
- Self-organizing map
Mechanisms¶
- Self-Organizing Map Training
- Unlike a distance-table method, it never sees a global distance matrix; it learns online, locally, on a grid.
This sourceKohonen's self-organizing system uses a one- or two-dimensional array of units with short-range feedback between neighbors to form a topologically ordered map.
- Unlike a distance-table method, it never sees a global distance matrix; it learns online, locally, on a grid.
Verification¶
Does it exist? Confirmed. This work's DOI resolves to a registered record, which fixes its identity. That is all it fixes.
Does it back the claim? Read against the text for 3 of 5 citations: 3 supported in part. Each verdict is shown under its citation below, with what in the work backs the sentence.
Support is checked per citation rather than per work — the same source can be cited soundly in one article and wrongly in another. Per-citation recording began recently, so a citation with no recorded check is a gap in the record rather than evidence it went unchecked.
See how references were verified.
Registry ID ref:0b6ea4515752 · see in the full table