Anda belum login :: 27 Nov 2024 04:08 WIB
Detail
ArtikelApproximation Bounds for Smooth Functions in C(IRd) By Neural and Mixture Networks  
Oleh: Maiorov, V. ; Meir, R. S.
Jenis: Article from Journal - ilmiah internasional
Dalam koleksi: IEEE Transactions on Neural Networks vol. 9 no. 5 (1998), page 969-978.
Topik: Finite mixture models; approximation; bounds; smooth functions; neural and mixture network
Ketersediaan
  • Perpustakaan Pusat (Semanggi)
    • Nomor Panggil: II36.3
    • Non-tandon: 1 (dapat dipinjam: 0)
    • Tandon: tidak ada
    Lihat Detail Induk
Isi artikelWe consider the approximation of smooth multivariate functions in C(Rd) by feedforward neural networks with a single hidden layer of nonlinear ridge functions. Under certain assumptions on the smoothness of the functions being approximated and on the activation functions in the neural network, we present upper bounds on the degree of approximation achieved over the domain Rd, thereby generalizing available results for compact domains. We extend the approximation results to the so - called mixture of expert architecture, which has received considerable attention in recent years, showing that the same type of approximation bound may be achieved.
Opini AndaKlik untuk menuliskan opini Anda tentang koleksi ini!

Kembali
design
 
Process time: 0.015625 second(s)