Characterization of set of vectors represented by lattices

被引:0
|
作者
Ho, Charlotte Yuk-Fan [1 ]
Ling, Bingo Wing-Kuen [2 ]
Nasir, Muhammad Habib Ullah [2 ]
Lam, Hak-Keung [2 ]
Iu, Herbert H. C. [3 ]
机构
[1] Univ London, Queen Mary Coll, Sch Math Sci, London, England
[2] Kings Coll London, Dept Elect Engn, London WC2R 2LS, England
[3] Univ Western Australia, Sch Elect, Elect & Comp Engn, Nedlands, WA 6009, Australia
来源
CSNDSP 08: PROCEEDINGS OF THE SIXTH INTERNATIONAL SYMPOSIUM ON COMMUNICATION SYSTEMS, NETWORKS AND DIGITAL SIGNAL PROCESSING | 2008年
关键词
D O I
10.1109/CSNDSP.2008.4610830
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
In this paper, the dynamics of weights of perceptrons are investigated based on the perceptron training algorithm. In particular, an invariant set of the weights of the perceptrons is defined and its properties are studied. By using these properties, a set of vectors that can be represented by integer combinations of a given set of lattices is characterized. If 1) the lattices are employed as training feature vectors of the perceptrons, 2) the threshold of the perceptrons is set to be zero, 3) an initial weight of the perceptrons is in an invariant set, 4) the corresponding desirable outputs and the initial weight of the perceptrons are chosen in such a way that the perceptrons exhibit chaotic behaviors, and 5) a vector is in the invariant set, then the vector can actually be represented as an integer combination of the lattices, and the sum of the half difference between the desirable downsampled outputs and the true downsampled outputs of the perceptron are the corresponding lattice code.
引用
收藏
页码:711 / +
页数:3
相关论文
共 50 条