Sciweavers

4080 search results - page 619 / 816
» The rebirth of neural networks
Sort
View
ICMCS
2000
IEEE
116views Multimedia» more  ICMCS 2000»
15 years 11 months ago
Non-linear Relevance Feedback: Improving the Performance of Content-Based Retrieval Systems
In this paper, a non-linear relevance feedback mechanism is proposed for increasing the performance and the reliability of content-based retrieval systems. In particular, the huma...
Nikolaos D. Doulamis, Anastasios D. Doulamis, Stef...
KES
2000
Springer
15 years 10 months ago
Hierarchical growing cell structures: TreeGCS
We propose a hierarchical, unsupervised clustering algorithm (TreeGCS) based upon the Growing Cell Structure (GCS) neural network of Fritzke. Our algorithm improves an inconsisten...
Victoria J. Hodge, James Austin
ICONIP
2007
15 years 8 months ago
Analysis on Bidirectional Associative Memories with Multiplicative Weight Noise
Abstract. In neural networks, network faults can be exhibited in different forms, such as node fault and weight fault. One kind of weight faults is due to the hardware or software ...
Chi-Sing Leung, Pui-Fai Sum, Tien-Tsin Wong
FLAIRS
2004
15 years 8 months ago
Invariance of MLP Training to Input Feature De-correlation
In the neural network literature, input feature de-correlation is often referred as one pre-processing technique used to improve the MLP training speed. However, in this paper, we...
Changhua Yu, Michael T. Manry, Jiang Li
BMVC
2000
15 years 8 months ago
Extraction of Motion Data from Image Sequences to Assist Animators
We describe a system which is designed to assist animators in extracting high-level information from sequences of images. The system is not meant to replace animators, but to be a...
David P. Gibson, Neill W. Campbell, Colin J. Dalto...