Sciweavers

310 search results - page 50 / 62
» Mapping from Speech to Images Using Continuous State Space M...
Sort
View
ICANN
2009
Springer
14 years 1 months ago
An EM Based Training Algorithm for Recurrent Neural Networks
Recurrent neural networks serve as black-box models for nonlinear dynamical systems identification and time series prediction. Training of recurrent networks typically minimizes t...
Jan Unkelbach, Yi Sun, Jürgen Schmidhuber
ESANN
2007
13 years 10 months ago
The Recurrent Control Neural Network
This paper presents our Recurrent Control Neural Network (RCNN), which is a model-based approach for a data-efficient modelling and control of reinforcement learning problems in di...
Anton Maximilian Schäfer, Steffen Udluft, Han...
TMI
2008
126views more  TMI 2008»
13 years 8 months ago
A Time Domain Fluorescence Tomography System for Small Animal Imaging
We describe the application of a time domain diffuse fluorescence tomography system for whole body small animal imaging. The key features of the system are the use of point excitat...
Anand T. N. Kumar, Scott B. Raymond, Andrew K. Dun...
FGR
2008
IEEE
203views Biometrics» more  FGR 2008»
14 years 2 months ago
Spatiotemporal pyramid representation for recognition of facial expressions and hand gestures
This paper presents a spatiotemporal pyramid representation for recognizing facial expressions and hand gestures. This approach works by partitioning video sequence into increasin...
Zhipeng Zhao, Ahmed M. Elgammal
SIAMADS
2010
122views more  SIAMADS 2010»
13 years 3 months ago
Local/Global Analysis of the Stationary Solutions of Some Neural Field Equations
Neural or cortical fields are continuous assemblies of mesoscopic models, also called neural masses, of neural populations that are fundamental in the modeling of macroscopic parts...
Romain Veltz, Olivier D. Faugeras