Sciweavers

IJCNN
2006
IEEE
14 years 2 months ago
Local Cluster Neural Network On-chip Training
Liang Zhang, Joaquin Sitte
IJCNN
2006
IEEE
14 years 2 months ago
C2FS: An Algorithm for Feature Selection in Cascade Neural Networks
Wrapper-based feature selection is attractive because wrapper methods are able to optimize the features they select to the specific learning algorithm. Unfortunately, wrapper met...
Lars Backstrom, Rich Caruana
IJCNN
2006
IEEE
14 years 2 months ago
Global Reinforcement Learning in Neural Networks with Stochastic Synapses
— We have found a more general formulation of the REINFORCE learning principle which had been proposed by R. J. Williams for the case of artificial neural networks with stochast...
Xiaolong Ma, Konstantin Likharev
IJCNN
2006
IEEE
14 years 2 months ago
Improvement of an Artificial Neural Network Model using Min-Max Preprocessing for the Prediction of Wave-induced Seabed Liquefac
—In the past decade, artificial neural networks (ANNs) have been widely applied to the engineering problems with a complicated system. ANNs are becoming an important alternative ...
Deaho Cha, Michael Blumenstein, Hong Zhang, Dong-S...
IJCNN
2006
IEEE
14 years 2 months ago
A Scalable FPGA Implementation of Cellular Neural Networks for Gabor-type Filtering
— We describe an implementation of Gabor-type filters on field programmable gate arrays using the cellular neural network (CNN) architecture. The CNN template depends upon the ...
Ocean Y. H. Cheung, Philip Heng Wai Leong, Eric K....
IJCNN
2006
IEEE
14 years 2 months ago
An optimization approach to achieve unsupervised segmentation and binding in a dynamical network
— We present a novel network of oscillatory units, whose behavior is described by the amplitude and phase of oscillations. While building on previous work, the system presented i...
A. Ravishankar Rao, Guillermo A. Cecchi, Charles C...
IJCNN
2006
IEEE
14 years 2 months ago
Backpropagation for Population-Temporal Coded Spiking Neural Networks
Abstract— Supervised learning rules for spiking neural networks are currently only able to use time-to-first-spike coding and are plagued by very irregular learning curves due t...
Benjamin Schrauwen, Jan M. Van Campenhout
IJCNN
2006
IEEE
14 years 2 months ago
How Not to Evaluate a Developmental System
—Computational models of development aim to describe the mechanisms that underlie the acquisition of new skills or the emergence of new capabilities. The strength of a model is j...
Frederick Shic, Brian Scassellati
IJCNN
2006
IEEE
14 years 2 months ago
Prototype based outlier detection
— Outliers refer to “minority” data that are different from most other data. They usually disturb data mining process. But, sometimes they provide valuable information. Thus,...
Seungtaek Kim, Sungzoon Cho
IJCNN
2006
IEEE
14 years 2 months ago
A Monte Carlo Sequential Estimation for Point Process Optimum Filtering
— Adaptive filtering is normally utilized to estimate system states or outputs from continuous valued observations, and it is of limited use when the observations are discrete e...
Yiwen Wang 0002, António R. C. Paiva, Jose ...