Sciweavers

737 search results - page 8 / 148
» Network Structuring and Training Using Rule-Based Knowledge
Sort
View
IJCNN
2006
IEEE
15 years 3 months ago
Effective Training Methods for Function Localization Neural Networks
— Inspired by Hebb’s cell assembly theory about how the brain worked, we have developed a function localization neural network (FLNN). The main part of a FLNN is structurally t...
Takafumi Sasakawa, Jinglu Hu, Katsunori Isono, Kot...
AAAI
2006
14 years 11 months ago
Cross-Domain Knowledge Transfer Using Structured Representations
Previous work in knowledge transfer in machine learning has been restricted to tasks in a single domain. However, evidence from psychology and neuroscience suggests that humans ar...
Samarth Swarup, Sylvian R. Ray
LREC
2010
164views Education» more  LREC 2010»
14 years 11 months ago
Learning to Mine Definitions from Slovene Structured and Unstructured Knowledge-Rich Resources
The paper presents an innovative approach to extract Slovene definition candidates from domain-specific corpora using morphosyntactic patterns, automatic terminology recognition a...
Darja Fiser, Senja Pollak, Spela Vintar
ECCV
2008
Springer
15 years 11 months ago
Training Hierarchical Feed-Forward Visual Recognition Models Using Transfer Learning from Pseudo-Tasks
Abstract. Building visual recognition models that adapt across different domains is a challenging task for computer vision. While feature-learning machines in the form of hierarchi...
Amr Ahmed, Kai Yu, Wei Xu, Yihong Gong, Eric P. Xi...
ICML
2006
IEEE
15 years 10 months ago
Discriminative unsupervised learning of structured predictors
We present a new unsupervised algorithm for training structured predictors that is discriminative, convex, and avoids the use of EM. The idea is to formulate an unsupervised versi...
Linli Xu, Dana F. Wilkinson, Finnegan Southey, Dal...