Name
Abstract | ||
|---|---|---|
TurSOM [1], short for Turing Self-Organizing Map, introduces new concepts, responsibilities and mechanisms to the traditional SOM algorithm. It draws its inspiration from Turing Unorganized Machines, competitive learning techniques, and SOM algorithms. Turing's unorganized machines (TUM) were one of the first computational concepts of modeling the cortex. Turing also described these machines as having self-organizing behaviors. The primary difference between Turing's self-organization description, and more traditional models we are familiar with (Grossberg, Kohonen), are that connections, rather than neurons, self-organize. TurSOM adheres to unsupervised, competitive learning techniques, wherein all neurons, and all connections between them are self-organizing and competing. As such, it presents a novel self-organizing neural network algorithm that eliminates the need for post-processing methods for cluster identification. |
Year | DOI | Venue |
|---|---|---|
2009 | 10.1109/IJCNN.2009.5178720 | IJCNN |
Keywords | Field | DocType |
cluster identification,turing self-organizing map,competitive learning technique,self-organizing map,tursom adheres,unorganized machines,traditional model,som algorithm,neural network algorithm,traditional som algorithm,self-organizing behavior,data mining,computational modeling,machine learning,self organization,competitive learning,artificial neural networks,clustering algorithms,turing machines,neural network,spirals,machine intelligence | Algorithm characterizations,Computer science,NSPACE,DSPACE,Super-recursive algorithm,Self-organizing map,Theoretical computer science,Turing machine,Artificial intelligence,Turing,Non-deterministic Turing machine,Machine learning | Conference |
ISSN | Citations | PageRank |
2161-4393 | 3 | 0.42 |
References | Authors | |
7 | 3 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Derek Beaton | 1 | 47 | 5.52 |
| Iren Valova | 2 | 136 | 25.44 |
| Daniel MacLean | 3 | 113 | 11.82 |