Sciweavers

4080 search results - page 270 / 816
» The rebirth of neural networks
Sort
View
ESWA
2010
118views more  ESWA 2010»
15 years 5 months ago
Integrating independent component analysis-based denoising scheme with neural network for stock price prediction
The forecasting of stock price is one of the most challenging tasks in investment/financial decision-making since stock prices/indices are inherently noisy and non-stationary. In ...
Chi-Jie Lu
IJCNN
2006
IEEE
16 years 20 days ago
Training Reformulated Product Units in Hybrid Neural Networks
— Higher order networks allow modelling of correlates and geometrically invariant properties. Current techniques for their development either require domain knowledge, or are con...
Philip T. Elliott, Diven Topiwala, Will N. Browne
ISCAS
2006
IEEE
70views Hardware» more  ISCAS 2006»
16 years 19 days ago
Power aware learning for class AB analogue VLSI neural network
—Recent research into artificial neural networks (ANN) has highlighted the potential of using compact analogue ANN hardware cores in embedded mobile devices, where power consumpt...
S. S. Modi, P. R. Wilson, A. D. Brown
GECCO
1999
Springer
133views Optimization» more  GECCO 1999»
15 years 11 months ago
Forecasting the MagnetoEncephaloGram (MEG) of Epileptic Patients Using Genetically Optimized Neural Networks
In this work MagnetoEncephaloGram (MEG) recordings of epileptic patients were analyzed using a hybrid neural networks training algorithm. This algorithm combines genetic algorithm...
Adam V. Adamopoulos, Efstratios F. Georgopoulos, S...
FLAIRS
2004
15 years 8 months ago
Simulating Biological Motion Perception Using a Recurrent Neural Network
People have the ability to perceive biological motion under conditions of severely limited visual information. If the information is in the form of a point-light motion sequence o...
Roxanne L. Canosa