Sciweavers

7 search results - page 1 / 2
» Constructive density estimation network based on several dif...
Sort
View
ESANN
2001
13 years 6 months ago
Constructive density estimation network based on several different separable transfer functions
Networks estimating probability density are usually based on radial basis function of the same type. Feature Space Mapping constructive network based on separable functions, optimi...
Wlodzislaw Duch, Rafal Adamczak, Geerd H. F. Dierc...
ESANN
2001
13 years 6 months ago
Transfer functions: hidden possibilities for better neural networks
Abstract. Sigmoidal or radial transfer functions do not guarantee the best generalization nor fast learning of neural networks. Families of parameterized transfer functions provide...
Wlodzislaw Duch, Norbert Jankowski
ICASSP
2008
IEEE
13 years 11 months ago
Encoding large array signals into a 3D sound field representation for selective listening point audio based on blind source sepa
A sound eld reproduction method which uses blind source separation and head-related transfer function is proposed. In the proposed system, multichannel acoustic signals captured a...
Kenta Niwa, Takanori Nishino, Kazuya Takeda
TEC
2010
191views more  TEC 2010»
12 years 11 months ago
Particle Swarm Optimization Aided Orthogonal Forward Regression for Unified Data Modeling
We propose a unified data modeling approach that is equally applicable to supervised regression and classification applications, as well as to unsupervised probability density func...
Sheng Chen, Xia Hong, Chris J. Harris
VLSID
2001
IEEE
132views VLSI» more  VLSID 2001»
14 years 5 months ago
Accurate Power Macro-modeling Techniques for Complex RTL Circuits
This paper presents novel techniques for the cycle-accurate power macro-modeling of complex RTL components. The proposed techniques are based on the observation that RTL component...
Nachiketh R. Potlapally, Michael S. Hsiao, Anand R...