Sciweavers

IJCNN
2007
IEEE
14 years 5 months ago
Self-Organizing Maps as Traveling Computational Templates
In this article we approach neural networks as computational templates that travel across various sciences. Traditionally, it has been thought that models are primarily models of s...
Tarja Knuuttila, Anna-Mari Rusanen, Timo Honkela
ICSNC
2007
IEEE
14 years 5 months ago
Movement Prediction Using Bayesian Learning for Neural Networks
Nowadays, path prediction is being extensively examined for use in the context of mobile and wireless computing towards more efficient network resource management schemes. Path pr...
Sherif Akoush, Ahmed Sameh
GLOBECOM
2007
IEEE
14 years 5 months ago
Minimizing Distribution Cost of Distributed Neural Networks in Wireless Sensor Networks
Abstract—This paper presents a novel study on how to distribute neural networks in a wireless sensor networks (WSNs) such that the energy consumption is minimized while improving...
Peng Guan, Xiaolin Li
CEC
2007
IEEE
14 years 5 months ago
Improving generalization capability of neural networks based on simulated annealing
— This paper presents a single-objective and a multiobjective stochastic optimization algorithms for global training of neural networks based on simulated annealing. The algorith...
Yeejin Lee, Jong-Seok Lee, Sun-Young Lee, Cheol Ho...
IJCNN
2008
IEEE
14 years 5 months ago
A comparison of architectural varieties in Radial Basis Function Neural Networks
— Representation of knowledge within a neural model is an active field of research involved with the development of alternative structures, training algorithms, learning modes an...
Mehmet Önder Efe, Cosku Kasnakoglu
IJCNN
2008
IEEE
14 years 5 months ago
Image clustering with spiking neuron network
— The process of segmenting images is one of the most critical ones in automatic image analysis whose goal can be regarded as to find what objects are presented in images. Artifi...
B. Meftah, A. Benyettou, Olivier Lezoray, W. QingX...
IJCNN
2008
IEEE
14 years 5 months ago
Numerical condition of feedforward networks with opposite transfer functions
— Numerical condition affects the learning speed and accuracy of most artificial neural network learning algorithms. In this paper, we examine the influence of opposite transfe...
Mario Ventresca, Hamid R. Tizhoosh
ICRA
2008
IEEE
143views Robotics» more  ICRA 2008»
14 years 5 months ago
Pattern generators with sensory feedback for the control of quadruped locomotion
— Central Pattern Generators (CPGs) are becoming a popular model for the control of locomotion of legged robots. Biological CPGs are neural networks responsible for the generatio...
Ludovic Righetti, Auke Jan Ijspeert
DATE
2008
IEEE
134views Hardware» more  DATE 2008»
14 years 5 months ago
Scalable Architecture for on-Chip Neural Network Training using Swarm Intelligence
This paper presents a novel architecture for on-chip neural network training using particle swarm optimization (PSO). PSO is an evolutionary optimization algorithm with a growing ...
Amin Farmahini Farahani, Seid Mehdi Fakhraie, Saee...
CEC
2008
IEEE
14 years 5 months ago
Creating edge detectors by evolutionary reinforcement learning
— In this article we present results from experiments where a edge detector was learned from scratch by EANT2, a method for evolutionary reinforcement learning. The detector is c...
Nils T. Siebel, Sven Grünewald, Gerald Sommer