New associative memories to recall real-valued patterns
被引:0
|
作者:
Sossa, H
论文数: 0引用数: 0
h-index: 0
机构:
IPN, Ctr Invest Computac, Mexico City 07738, DF, MexicoIPN, Ctr Invest Computac, Mexico City 07738, DF, Mexico
Sossa, H
[1
]
Barrón, R
论文数: 0引用数: 0
h-index: 0
机构:
IPN, Ctr Invest Computac, Mexico City 07738, DF, MexicoIPN, Ctr Invest Computac, Mexico City 07738, DF, Mexico
Barrón, R
[1
]
Váquez, RA
论文数: 0引用数: 0
h-index: 0
机构:
IPN, Ctr Invest Computac, Mexico City 07738, DF, MexicoIPN, Ctr Invest Computac, Mexico City 07738, DF, Mexico
Váquez, RA
[1
]
机构:
[1] IPN, Ctr Invest Computac, Mexico City 07738, DF, Mexico
来源:
PROGRESS IN PATTERN RECOGNITION, IMAGE ANALYSIS AND APPLICATIONS
|
2004年
/
3287卷
关键词:
D O I:
暂无
中图分类号:
TP18 [人工智能理论];
学科分类号:
081104 ;
0812 ;
0835 ;
1405 ;
摘要:
In this note we describe a new set of associative memories able to recall patterns in the presence of mixed noise. Conditions are given under which the proposed memories are able to recall patterns either from the fundamental set of patterns and from distorted versions of them. Numerical and real examples are also provided to show the efficiency of the proposal.
机构:
Univ Buenos Aires, Fac Ciencias Exactas & Nat, Dept Matemat, RA-1428 Buenos Aires, DF, ArgentinaUniv Buenos Aires, Fac Ciencias Exactas & Nat, Dept Matemat, RA-1428 Buenos Aires, DF, Argentina
Cignoli, Roberto
Marra, Vincenzo
论文数: 0引用数: 0
h-index: 0
机构:
Univ Milan, Dipartimento Informat & Comunicaz, I-20135 Milan, ItalyUniv Buenos Aires, Fac Ciencias Exactas & Nat, Dept Matemat, RA-1428 Buenos Aires, DF, Argentina