Limitations of Nonlinear PCA as Performed With Generic Neural Networks  

Oleh:

Malthouse, E. C.

Jenis: Article from Journal - ilmiah internasional
Dalam koleksi: IEEE Transactions on Neural Networks vol. 9 no. 1 (1998), page 165-173.
Topik: GENERICALNESS(LINGUISTICS); limitations; non linear; PCA; generic; neural network

Ketersediaan

Perpustakaan Pusat (Semanggi) Nomor Panggil: II36.3 Non-tandon: 1 (dapat dipinjam: 0) Tandon: tidak ada

Lihat Detail Induk

Isi artikel

Kramer's (1991) non linear principal components analysis (NLPCA) neural networks are feedforward auto associative networks with five layers. The third layer has fewer nodes than the input or output layers. This paper proposes a geometric interpretation for Kramer's method by showing that NLPCA fits a lower - dimensional curve or surface through the training data. The first three layers project observations onto the curve or surface giving scores. The last three layers define the curve or surface. The first three layers are a continuous function, which we show has several implications : NLPCA “projections” are suboptimal producing larger approximation error, NLPCA is unable to model curves and surfaces that intersect themselves, and NLPCA cannot parameterize curves with parameterizations having discontinuous jumps. We establish results on the identification of score values and discuss their implications on interpreting score values. We discuss the relationship between NLPCA and principal curves and surfaces, another non linear feature extraction method.

Opini Anda

Klik untuk menuliskan opini Anda tentang koleksi ini!

Kembali