Sciweavers

4864 search results - page 815 / 973
» Evolving neural networks
Sort
View
121
Voted
IJCAI
2007
15 years 3 months ago
A Fully Connectionist Model Generator for Covered First-Order Logic Programs
We present a fully connectionist system for the learning of first-order logic programs and the generation of corresponding models: Given a program and a set of training examples,...
Sebastian Bader, Pascal Hitzler, Steffen Höll...
STOC
2010
ACM
170views Algorithms» more  STOC 2010»
15 years 6 months ago
Connectivity oracles for failure prone graphs
Dynamic graph connectivity algorithms have been studied for many years, but typically in the most general possible setting, where the graph can evolve in completely arbitrary ways...
Ran Duan, Seth Pettie
CIDM
2009
IEEE
15 years 8 months ago
Ensemble member selection using multi-objective optimization
— Both theory and a wealth of empirical studies have established that ensembles are more accurate than single predictive models. Unfortunately, the problem of how to maximize ens...
Tuve Löfström, Ulf Johansson, Henrik Bos...
112
Voted
IJCNN
2008
IEEE
15 years 8 months ago
Including multi-objective abilities in the Hybrid Intelligent Suite for decision support
— Hybrid intelligent systems (HIS) are very successful in tackling problems comprising of more than one distinct computational subtask. For instance, decision-making problems are...
Diogo Ferreira Pacheco, Flávio R. S. Olivei...
IWANN
2007
Springer
15 years 8 months ago
Towards the Integration of a Bioprofile in Ocular Melanoma
Approximately 50% of all patients with intraocular melanoma die of metastatic disease, despite successful treatment of the primary tumour. The main factors associated with mortalit...
Azzam F. Taktak, Antonio Eleuteri, Christian Setzk...