Sciweavers

91 search results - page 9 / 19
» Fast convergence in evolutionary models: A Lyapunov approach
Sort
View
ICDM
2010
IEEE
167views Data Mining» more  ICDM 2010»
15 years 4 months ago
Averaged Stochastic Gradient Descent with Feedback: An Accurate, Robust, and Fast Training Method
On large datasets, the popular training approach has been stochastic gradient descent (SGD). This paper proposes a modification of SGD, called averaged SGD with feedback (ASF), tha...
Xu Sun, Hisashi Kashima, Takuya Matsuzaki, Naonori...
IROS
2007
IEEE
127views Robotics» more  IROS 2007»
16 years 20 days ago
Dynamic redistribution of a swarm of robots among multiple sites
Abstract— We present an approach for the dynamic assignment and reassignment of a large team of homogeneous robotic agents to multiple locations with applications to search and r...
Ádám M. Halász, M. Ani Hsieh,...
ICIAR
2004
Springer
15 years 11 months ago
Real-Time Facial Feature Extraction by Cascaded Parameter Prediction and Image Optimization
We propose a new fast facial-feature extraction technique for embedded face-recognition applications. A deformable feature model is adopted, of which the parameters are optimized t...
Fei Zuo, Peter H. N. de With
ICCV
2001
IEEE
16 years 8 months ago
Gradient Vector Flow Fast Geodesic Active Contours
This paper proposes a new front propagation flow for boundary extraction. The proposed framework is inspired by the geodesic active contour model and leads to a paradigm that is r...
Nikos Paragios, Olivier Mellina-Gottardo, Visvanat...
CEC
2008
IEEE
16 years 25 days ago
On the generality of the evolved driving rules of an agent operating a model of a car
—We present an approach for automated evolutionary design of the functionary of driving agent, able to operate a software model of fast running car. The objective of our work is ...
Hirotaka Yamazaki, Ivan Tanev, Tomoyuki Hiroyasu, ...