Sciweavers

2210 search results - page 110 / 442
» Information complexity of neural networks
Sort
View
ICONIP
2010
15 years 3 months ago
Emergence of Highly Nonrandom Functional Synaptic Connectivity Through STDP
Abstract. We investigated the network topology organized through spike-timingdependent plasticity (STDP) using pair- and triad-connectivity patterns, considering di erence of excit...
Hideyuki Kato, Tohru Ikeguchi
WSOM
2009
Springer
16 years 1 months ago
Incremental Unsupervised Time Series Analysis Using Merge Growing Neural Gas
We propose Merge Growing Neural Gas (MGNG) as a novel unsupervised growing neural network for time series analysis. MGNG combines the state-of-the-art recursive temporal context of...
Andreas Andreakis, Nicolai von Hoyningen-Huene, Mi...
IJCNN
2008
IEEE
16 years 24 days ago
Dataset complexity can help to generate accurate ensembles of k-nearest neighbors
— Gene expression based cancer classification using classifier ensembles is the main focus of this work. A new ensemble method is proposed that combines predictions of a small ...
Oleg Okun, Giorgio Valentini
AMT
2006
Springer
107views Multimedia» more  AMT 2006»
15 years 10 months ago
An Intelligent Process Monitoring System in Complex Manufacturing Environment
In high-tech industries, most manufacturing processes are complexly intertwined, in that manufacturers or engineers can hardly control a whole set of processes. They are only capa...
Sung Ho Ha, Boo-Sik Kang
CORR
2008
Springer
208views Education» more  CORR 2008»
15 years 6 months ago
Equilibria, Fixed Points, and Complexity Classes
Many models from a variety of areas involve the computation of an equilibrium or fixed point of some kind. Examples include Nash equilibria in games; market equilibria; computing o...
Mihalis Yannakakis