High-Order MS_CMAC Neural Network  

Oleh:

Jan, J. C. ; Hung, Shih-Lin

Jenis: Article from Journal - ilmiah internasional
Dalam koleksi: IEEE Transactions on Neural Networks vol. 12 no. 3 (2001), page 598-603.
Topik: neural network; high - order; MS_CMAC; neural network

Ketersediaan

Perpustakaan Pusat (Semanggi) Nomor Panggil: II36.5 Non-tandon: 1 (dapat dipinjam: 0) Tandon: tidak ada

Lihat Detail Induk

Isi artikel

A macro structure cerebellar model articulation controller (MS CMAC) was developed by connecting several 1D CMAC in a tree structure, which decomposes a multidimensional problem into a set of 1D subproblems, to reduce the computational complexity in multidimensional CMAC. Additionally, a trapezium scheme is proposed to assist MS CMAC to model non linear systems. However, this trapezium scheme cannot perform a real smooth interpolation, and its working parameters are obtained through cross - validation. A quadratic splines scheme is developed herein to replace the trapezium scheme in MS CMAC, named high - order MS CMAC (HMS CMAC). The quadratic splines scheme systematically transforms the stepwise weight contents of CMAC in MS CMAC into smooth weight contents to perform the smooth outputs. Test results affirm that the HMS CMAC has acceptable generalization in continuous function - mapping problems for non overlapping association in training instances. Non overlapping association in training instances not only significantly reduces the number of training instances needed, but also requires only one learning cycle in the learning stage.

Opini Anda

Klik untuk menuliskan opini Anda tentang koleksi ini!

Kembali