A Self-Organizing Map for Adaptive Processing of Structured Data  

Oleh:

Ah, Chung Tsoi ; Sperduti, A. ; Hagenbuchner, M.

Jenis: Article from Journal - ilmiah internasional
Dalam koleksi: IEEE Transactions on Neural Networks vol. 14 no. 3 (May 2003), page 491-505.
Topik: MAPS; self - organizing; map; adaptive process; structured data

Ketersediaan

Perpustakaan Pusat (Semanggi) Nomor Panggil: II36.7 Non-tandon: 1 (dapat dipinjam: 0) Tandon: tidak ada

Lihat Detail Induk

Isi artikel

Recent developments in the area of neural networks produced models capable of dealing with structured data. Here, we propose the first fully unsupervised model, namely an extension of traditional self - organizing maps (SOMs), for the processing of labeled directed acyclic graphs (DAG s). The extension is obtained by using the unfolding procedure adopted in recurrent and recursive neural networks, with the replicated neurons in the unfolded network comprising of a full SOM. This approach enables the discovery of similarities among objects including vectors consisting of numerical data. The capabilities of the model are analyzed in detail by utilizing a relatively large data set taken from an artificial benchmark problem involving visual patterns encoded as labeled DAG s. The experimental results demonstrate clearly that the proposed model is capable of exploiting both information conveyed in the labels attached to each node of the input DAG s and information encoded in the DAG topology.

Opini Anda

Klik untuk menuliskan opini Anda tentang koleksi ini!

Kembali