Multidimensional Wavelet Networks based on a Tensor Product Structure  

Oleh:

Jian Wan ; Qing Li ; Demin Xu ; Yuyao He

Jenis: Article from Article
Dalam koleksi: Final Program and Book of Abstracts: The 4th Asian Control Conference, September 25-27, 2002 (Sep. 2002), page 2174-2179.
Topik: Wavelet; Networks; Tensor; Product Sensor
Fulltext: AC021020.PDF (149.07KB)

Isi artikel

Based on the wavelet frame theory, a novel wavelet network for function learning in multidimensional spaces is proposed to avoid the ‘curse of dimensionality’. The main feature of the wavelet network proposed is to multiply the reconstruction of each dimension in the output layer instead of adding them as usual. Thus a multidimensional wavelet frame will be generated automatically and function learning can also be realized through online or off-line adjustment of weight coefficients. Design methods for one-dimensional wavelet networks can also be generalized straightforwardly to multidimensional cases by using the product structure. In the experiments, the multidimensional wavelet network performed well and compared favorably to the MLP and former wavelet networks.

Opini Anda

Klik untuk menuliskan opini Anda tentang koleksi ini!

Kembali