Abstract | ||
---|---|---|
We present a novel unsupervised artificial neural network for the extraction of common features in multiple data sources. This algorithm, which we name Exploratory Correlation Anal- ysis (ECA), is a multi-stream extension of a neural imple- mentation of Exploratory Projection Pursuit (EPP) and has a close relationship with Canonical Correlation Analysis (CCA). Whereas EPP identifies "interesting" statistical directions in a single stream of data, ECA develops a joint coding of the common underlying statistical features across a number of data streams. It has been shown that the principle of con- textual guidance may be used to find a sparse coding of the features in dual natural image patches that is very dif- ferent from single stream sparse coding experiments. The network only identifies those features which exist in both data streams and thus tend to be fewer in number and more complex in nature. |
Year | Venue | Keywords |
---|---|---|
2002 | ESANN | sparse coding,artificial neural network,projection pursuit,canonical correlation analysis |
Field | DocType | Citations |
Multiple data,Data stream mining,Projection pursuit,Pattern recognition,Neural coding,Computer science,Canonical correlation,Coding (social sciences),Artificial intelligence,Artificial neural network,Machine learning,Correlation analysis | Conference | 4 |
PageRank | References | Authors |
0.50 | 5 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jos Koetsier | 1 | 51 | 7.81 |
Donald Macdonald | 2 | 117 | 9.79 |
Darryl Charles | 3 | 85 | 16.25 |
Colin Fyfe | 4 | 508 | 55.62 |