Teuvo Kohonen
In plain wordsA Finnish engineer who invented the self-organizing map, a neural network that arranges complex data on a simple grid so that similar items end up next to each other.
Finnish engineer and professor at the Helsinki University of Technology, best known for the self-organizing mapself-organizing map, n.: A neural network that arranges data on a flat grid so that similar items end up in neighboring cells, producing a map of how the data is organized. (1982), an unsupervised learningunsupervised learning, n.: Machine learning without answer keys: the computer looks at unlabeled data and finds structure on its own, such as groups of similar customers or the main ways in which data vary. network that arranges its units on a low-dimensional grid so that similar inputs activate neighboring units, producing topology-preserving maps of high-dimensional data. Earlier he developed correlation-matrix associative memoriesassociative memory, n.: A memory that is searched by content rather than by location: given part of a stored pattern, or a noisy copy of it, it recalls the whole, much as a few notes can bring back an entire song. (1972), independently of James Anderson, and he later introduced learning vector quantization (1986), a supervised prototype-based classifier, and applied his networks to speech recognition with a neural 'phonetic typewriter' for Finnish (1988). Self-organizing maps became standard tools for clusteringclustering, n.: Automatically sorting things into groups of similar items when nobody has said in advance what the groups should be, like sorting a drawer of odd socks into piles by color and size., visualization and exploratory data analysis in fields from finance to bioinformatics before methods such as t-SNEt-SNE, n.: A technique for drawing data that have many measurements per item as a flat map in which similar items land close together, widely used to look for groups in AI models' internal data or in genetic data. and UMAPUMAP, n.: A fast technique for turning data with many measurements per item into a flat map that keeps similar items together; often preferred to older methods because it is quicker and copes with more data., and for decades he was among the most cited European researchers in neural networks. His honors include the IEEE Frank Rosenblatt Award (2008).
Related
- self-organizing mapself-organizing map, n.: A neural network that arranges data on a flat grid so that similar items end up in neighboring cells, producing a map of how the data is organized.
- unsupervised learningunsupervised learning, n.: Machine learning without answer keys: the computer looks at unlabeled data and finds structure on its own, such as groups of similar customers or the main ways in which data vary.
- associative memoryassociative memory, n.: A memory that is searched by content rather than by location: given part of a stored pattern, or a noisy copy of it, it recalls the whole, much as a few notes can bring back an entire song.
- clusteringclustering, n.: Automatically sorting things into groups of similar items when nobody has said in advance what the groups should be, like sorting a drawer of odd socks into piles by color and size.
- dimensionality reductiondimensionality reduction, n.: Squeezing data that has many measurements per item into far fewer numbers while keeping the patterns that matter, so it is easier to visualize, store or learn from.
Sources
- Kohonen, T. (1982). Self-Organized Formation of Topologically Correct Feature Maps. Biological Cybernetics 43(1): 59–69.
- Kohonen, T. (2001). Self-Organizing Maps (3rd ed.). Springer.