Sciweavers

462 search results - page 74 / 93
» Verifying Properties of Neural Networks
Sort
View
COMPGEOM
1997
ACM
13 years 11 months ago
Realistic Input Models for Geometric Algorithms
Many algorithms developed in computational geometry are needlessly complicated and slow because they have to be prepared for very complicated, hypothetical inputs. To avoid this, ...
Mark de Berg, Matthew J. Katz, A. Frank van der St...
HOTDEP
2008
107views Hardware» more  HOTDEP 2008»
13 years 9 months ago
Reverse-Engineering Drivers for Safety and Portability
Device drivers today lack two important properties: guaranteed safety and cross-platform portability. We present an approach to incrementally achieving these properties in drivers...
Vitaly Chipounov, George Candea
IDA
1998
Springer
13 years 7 months ago
Self-Organized-Expert Modular Network for Classification of Spatiotemporal Sequences
We investigate a form of modular neural network for classification with (a) pre-separated input vectors entering its specialist (expert) networks, (b) specialist networks which ar...
Sylvian R. Ray, William H. Hsu
IJCNN
2006
IEEE
14 years 1 months ago
Comparing Kernels for Predicting Protein Binding Sites from Amino Acid Sequence
— The ability to identify protein binding sites and to detect specific amino acid residues that contribute to the specificity and affinity of protein interactions has importan...
Feihong Wu
MICAI
2004
Springer
14 years 26 days ago
A Biologically Motivated and Computationally Efficient Natural Language Processor
Abstract. Conventional artificial neural network models lack many physiological properties of the neuron. Current learning algorithms are more concerned to computational performanc...
João Luís Garcia Rosa