Sciweavers

1136 search results - page 34 / 228
» Learning with Weighted Transducers
Sort
View
VISUAL
1999
Springer
14 years 1 months ago
Genetic Algorithm for Weights Assignment in Dissimilarity Function for Trademark Retrieval
Abstract. Trademark image retrieval is becoming an important application for logo registry, veri cation, and design. There are two major problems about the current approaches to tr...
David Yuk-Ming Chan, Irwin King
IJCNN
2008
IEEE
14 years 3 months ago
Shedding weights: More with less
—Traditional connectionist classification models place an emphasis on learned synaptic weights. Based on neurobiological evidence, a new approach is developed and experimentally ...
Tsvi Achler, Cyrus Omar, Eyal Amir
AUSAI
2003
Springer
14 years 2 months ago
Weighted MCRDR: Deriving Information about Relationships between Classifications in MCRDR
Multiple Classification Ripple Down Rules (MCRDR) is a knowledge acquisition technique that produces representations, or knowledge maps, of a human expert’s knowledge of a partic...
Richard Dazeley, Byeong Ho Kang
IJCNN
2007
IEEE
14 years 3 months ago
A Novel Weighted LBG Algorithm for Neural Spike Compression
Abstract— In this paper, we present a weighted Linde-BuzoGray algorithm (WLBG) as a powerful and efficient technique for compressing neural spike data. We compare this technique...
Sudhir Rao, António R. C. Paiva, Jose C. Pr...
COMPLEXITY
2008
84views more  COMPLEXITY 2008»
13 years 9 months ago
Evolutionary learning of small networks
Results are presented of a simulation which mimics an evolutionary learning process for small networks. Special features of these networks include a high recurrency, a transition ...
Thomas Filk, Albrecht von Müller