Sciweavers

IJCNN
2008
IEEE
14 years 6 months ago
Self-organizing neural models integrating rules and reinforcement learning
— Traditional approaches to integrating knowledge into neural network are concerned mainly about supervised learning. This paper presents how a family of self-organizing neural m...
Teck-Hou Teng, Zhong-Ming Tan, Ah-Hwee Tan
IJCNN
2008
IEEE
14 years 6 months ago
A network model of rational versus irrational choices on a probability maximization task
─Humans have a drive to maximize knowledge of the world, yet decision making data also suggest a contrary drive to minimize cognitive effort using simplifying heuristics. The tra...
Daniel S. Levine, Leonid I. Perlovsky
IJCNN
2008
IEEE
14 years 6 months ago
Lazy Self-Organizing Map and its behaviors
— The Self-Organizing Map (SOM) is a famous algorithm for the unsupervised learning and visualization introduced by Teuvo Kohonen. This study proposes the Lazy SelfOrganizing Map...
Taku Haraguchi, Haruna Matsushita, Yoshifumi Nishi...
IJCNN
2008
IEEE
14 years 6 months ago
Biologically realizable reward-modulated hebbian training for spiking neural networks
— Spiking neural networks have been shown capable of simulating sigmoidal artificial neural networks providing promising evidence that they too are universal function approximat...
Silvia Ferrari, Bhavesh Mehta, Gianluca Di Muro, A...
IJCNN
2008
IEEE
14 years 6 months ago
An EEG-based BCI system for 2D cursor control
Abstract— In this paper, an electroencephalogram (EEG)based brain computer interface (BCI) is proposed for two dimensional cursor control. The horizontal and vertical movements o...
Yuanqing Li, Chuanchu Wang, Haihong Zhang, Cuntai ...
IJCNN
2008
IEEE
14 years 6 months ago
A connection-limited neural network by InfoMax and InfoMin
— It is well known that edge filters in the visual system can be generated by the InfoMax principle. But, such models are nonlinear and employ fully-connected network structures...
Yoshitatsu Matsuda, Kazunori Yamaguchi
IJCNN
2008
IEEE
14 years 6 months ago
Two-level clustering approach to training data instance selection: A case study for the steel industry
— Nowadays, huge amounts of information from different industrial processes are stored into databases and companies can improve their production efficiency by mining some new kn...
Heli Koskimäki, Ilmari Juutilainen, Perttu La...
IJCNN
2008
IEEE
14 years 6 months ago
Fuzzy Adaptive Resonance Theory Combining Overlapped Category in consideration of connections
Abstract— Adaptive Resonance Theory (ART) is an unsupervised neural network. Fuzzy ART (FART) is a variation of ART, allows both binary and continuous input patterns. However, Fu...
Haruka Isawa, Haruna Matsushita, Yoshifumi Nishio
ICTAI
2008
IEEE
14 years 6 months ago
An Incremental Hough Transform for Detecting Ellipses in Image Data Streams
In this paper, we present a purely incremental, scalable algorithm for the detection of elliptical shapes in images. Our method uses an incremental version of the Random Hough Tra...
Sofiane Sellah, Olfa Nasraoui
ICTAI
2008
IEEE
14 years 6 months ago
Probabilistic Continuous Constraint Satisfaction Problems
Constraint programming has been used in many applications where uncertainty arises to model safe reasoning. The goal of constraint propagation is to propagate intervals of uncerta...
Elsa Carvalho, Jorge Cruz, Pedro Barahona