Sciweavers

388 search results - page 56 / 78
» Convergence Properties of the K-Means Algorithms
Sort
View
ICANN
2007
Springer
15 years 1 months ago
Solving Selected Classification Problems in Bioinformatics Using Multilayer Neural Network Based on Multi-Valued Neurons (MLMVN)
A multilayer neural network based on multi-valued neurons (MLMVN) is a new powerful tool for solving classification, recognition and prediction problems. This network has a number ...
Igor N. Aizenberg, Jacek M. Zurada
ICGA
1993
145views Optimization» more  ICGA 1993»
15 years 1 months ago
Genetic Programming of Minimal Neural Nets Using Occam's Razor
A genetic programming method is investigated for optimizing both the architecture and the connection weights of multilayer feedforward neural networks. The genotype of each networ...
Byoung-Tak Zhang, Heinz Mühlenbein
CORR
2010
Springer
114views Education» more  CORR 2010»
14 years 11 months ago
On the Stability of Empirical Risk Minimization in the Presence of Multiple Risk Minimizers
Abstract--Recently Kutin and Niyogi investigated several notions of algorithmic stability--a property of a learning map conceptually similar to continuity--showing that training-st...
Benjamin I. P. Rubinstein, Aleksandr Simma
AUTOMATICA
2006
111views more  AUTOMATICA 2006»
14 years 11 months ago
The minimal disturbance invariant set: Outer approximations via its partial sums
This paper is concerned with outer approximations of the minimal disturbance invariant set (MDIS) of a discrete-time linear system with an additive set-bounded disturbance. The k-...
Chong Jin Ong, Elmer G. Gilbert
CN
2007
102views more  CN 2007»
14 years 11 months ago
The "Global-ISP" paradigm
We present a new paradigm, called “Global ISP” (G-ISP). Its goal is to solve, or at least alleviate, problems of inter-domain routing, such as slow convergence, and lack of Qo...
Reuven Cohen, Amnon Shochot