Sciweavers

186 search results - page 11 / 38
» Computational Properties of Probabilistic Neural Networks
Sort
View
SOFSEM
2004
Springer
14 years 27 days ago
Approaches Based on Markovian Architectural Bias in Recurrent Neural Networks
Recent studies show that state-space dynamics of randomly initialized recurrent neural network (RNN) has interesting and potentially useful properties even without training. More p...
Matej Makula, Michal Cernanský, Lubica Benu...
CIBCB
2005
IEEE
14 years 1 months ago
A Neural Network for Predicting Protein Disorder using Amino Acid Hydropathy Values
— Proteins have been discovered to contain ordered regions and disordered regions, where ordered regions have a defined three-dimensional (3D) structure and disordered regions d...
Deborah Stoffer, L. Gwenn Volkert
IJCNN
2006
IEEE
14 years 1 months ago
Correntropy: A Localized Similarity Measure
—The measure of similarity normally utilized in statistical signal processing is based on second order moments. In this paper, we reveal the probabilistic meaning of correntropy ...
Weifeng Liu, Puskal P. Pokharel, Jose C. Principe
IJON
2007
84views more  IJON 2007»
13 years 7 months ago
Modeling self-developing biological neural networks
Recent progress in chips–neuron interface suggests real biological neurons as long-term alternatives to silicon transistors. The first step ning such computing systems is to bu...
Hugues Berry, Olivier Temam
EVOW
2006
Springer
13 years 11 months ago
Continuous-Time Recurrent Neural Networks for Generative and Interactive Musical Performance
This paper describes an ongoing exploration into the use of Continuous-Time Recurrent Neural Networks (CTRNNs) as generative and interactive performance tools, and using Genetic Al...
Oliver Bown, Sebastian Lexer