Abstract | ||
---|---|---|
The paper introduces new valuable improvements of performance, a construction and a topology optimization of the Self-Optimizing Neural Networks (SONNs). In contrast to the previous version (SONN-2), the described SONN-3 integrates the very effective solutions used in the SONN-2 with the very effective ADFA algorithms for an automatic conversion of real inputs into binary inputs. The SONN-3 is a fully constructive ontogenic neural network classificator based on a sophisticated training data analysis that quickly estimates values of individual real, integer or binary input features. This method carries out all computation fully automatically from a data analysis and a data input dimension reduction to a computation of a neural network topology and its weight parameters. Moreover, the SONN-3 computational cost is equal O(nlog2n), where nis a sum of a data quantity, a data input dimension and a data output dimension. The results of the SONN-3 construction and optimization are illustrated and compared by means of some examples. |
Year | DOI | Venue |
---|---|---|
2008 | 10.1007/978-3-540-87559-8_79 | ICANN (2) |
Keywords | Field | DocType |
data output dimension,data quantity,data analysis,data input dimension reduction,sonn-3 computational cost,data input dimension,sonn-3 construction,sophisticated training data analysis,binary input feature,optimization aspects,binary input,topology optimization,artificial intelligent,neural network,dimension reduction | Integer,Training set,Dimensionality reduction,Constructive,Computer science,Theoretical computer science,Topology optimization,Artificial intelligence,Artificial neural network,Machine learning,Computation,Binary number | Conference |
Volume | ISSN | Citations |
5164 | 0302-9743 | 1 |
PageRank | References | Authors |
0.43 | 4 | 1 |
Name | Order | Citations | PageRank |
---|---|---|---|
Adrian Horzyk | 1 | 53 | 12.76 |