Feedforward Sigmoidal Networks - Equicontinuity and Fault-Tolerance Properties  

Oleh:

Chandra, P. ; Singh, Y.

Jenis: Article from Journal - ilmiah internasional
Dalam koleksi: IEEE Transactions on Neural Networks vol. 15 no. 6 (Nov. 2004), page 1350-1366.
Topik: TOLERANCE; sigmoidal networks; equicontinuity; fault -tolerance; properties

Ketersediaan

Perpustakaan Pusat (Semanggi) Nomor Panggil: II36.11 Non-tandon: 1 (dapat dipinjam: 0) Tandon: tidak ada

Lihat Detail Induk

Isi artikel

Sigmoidal feedforward artificial neural networks (FFANN s) have been established to be universal approximators of continuous functions. The universal approximation results are summarized to identify the function sets represented by the sigmoidal FFANN s with the universal approximation properties. The equicontinuous properties of the identified sets is analyzed. The equicontinuous property is related to the fault tolerance of the sigmoidal FFANN s. The generally used arbitrary weight sigmoidal FFANN s are shown to be non equicontinuous sets. A class of bounded weight sigmoidal FFANN s is established to be equicontinuous. The fault - tolerance behaviour of the networks is analyzed and error bounds for the induced errors established.

Opini Anda

Klik untuk menuliskan opini Anda tentang koleksi ini!

Kembali