Sciweavers

619 search results - page 10 / 124
» On computational limitations of neural network architectures
Sort
View
IJCNN
2006
IEEE
14 years 1 months ago
An Integrated Soft Computing Approach for Predicting Biological Activity of Potential HIV-1 Protease Inhibitors
Abstract— Using a neural network-fuzzy logic-genetic algorithm approach we generate an optimal predictor for biological activities of HIV-1 protease potential inhibitory compound...
Razvan Andonie, Levente Fabry-Asztalos, Sarah Abdu...
SBACPAD
2008
IEEE
249views Hardware» more  SBACPAD 2008»
14 years 1 months ago
Processing Neocognitron of Face Recognition on High Performance Environment Based on GPU with CUDA Architecture
This work presents an implementation of Neocognitron Neural Network, using a high performance computing architecture based on GPU (Graphics Processing Unit). Neocognitron is an ar...
Gustavo Poli, José Hiroki Saito, Joã...
IPPS
2000
IEEE
13 years 12 months ago
Using Time Skewing to Eliminate Idle Time due to Memory Bandwidth and Network Limitations
Time skewing is a compile-time optimization that can provide arbitrarily high cache hit rates for a class of iterative calculations, given a sufficient number of time steps and s...
David Wonnacott
CORR
2004
Springer
106views Education» more  CORR 2004»
13 years 7 months ago
Intelligent Systems: Architectures and Perspectives
: The integration of different learning and adaptation techniques to overcome individual limitations and to achieve synergetic effects through the hybridization or fusion of these ...
Ajith Abraham
NPL
2002
145views more  NPL 2002»
13 years 7 months ago
Hybrid Feedforward Neural Networks for Solving Classification Problems
A novel multistage feedforward network is proposed for efficient solving of difficult classification tasks. The standard Radial Basis Functions (RBF) architecture is modified in or...
Iulian B. Ciocoiu