Sciweavers

100 search results - page 13 / 20
» Evolving recurrent models using linear GP
Sort
View
NIPS
2001
13 years 9 months ago
Learning Lateral Interactions for Feature Binding and Sensory Segmentation
We present a new approach to the supervised learning of lateral interactions for the competitive layer model (CLM) dynamic feature binding architecture. The method is based on con...
Heiko Wersing
ESANN
2008
13 years 9 months ago
An FPGA-based model suitable for evolution and development of spiking neural networks
We propose a digital neuron model suitable for evolving and growing heterogeneous spiking neural networks on FPGAs using a piecewise linear approximation of the Quadratic Integrate...
Hooman Shayani, Peter J. Bentley, Andrew M. Tyrrel...
EVOW
2003
Springer
14 years 1 months ago
Comparison of AdaBoost and Genetic Programming for Combining Neural Networks for Drug Discovery
Genetic programming (GP) based data fusion and AdaBoost can both improve in vitro prediction of Cytochrome P450 activity by combining artificial neural networks (ANN). Pharmaceuti...
William B. Langdon, S. J. Barrett, Bernard F. Buxt...
SMI
2008
IEEE
116views Image Analysis» more  SMI 2008»
14 years 2 months ago
Self-organizing primitives for automated shape composition
Motivated by the ability of living cells to form into specific shapes and structures, we present a new approach to shape modeling based on self-organizing primitives whose behavi...
Linge Bai, Manolya Eyiyurekli, David E. Breen
JCB
2007
97views more  JCB 2007»
13 years 7 months ago
Parsing Nucleic Acid Pseudoknotted Secondary Structure: Algorithm and Applications
Accurate prediction of pseudoknotted nucleic acid secondary structure is an important computational challenge. Prediction algorithms based on dynamic programming aim to find a st...
Baharak Rastegari, Anne Condon