Sciweavers

388 search results - page 56 / 78
» Convergence Properties of the K-Means Algorithms
Sort
View
ICANN
2007
Springer
15 years 3 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 2 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»
15 years 1 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»
15 years 1 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»
15 years 1 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