Sciweavers

986 search results - page 114 / 198
» Zero-data Learning of New Tasks
Sort
View
ICDAR
2009
IEEE
15 years 4 months ago
Evaluating Retraining Rules for Semi-Supervised Learning in Neural Network Based Cursive Word Recognition
Training a system to recognize handwritten words is a task that requires a large amount of data with their correct transcription. However, the creation of such a training set, inc...
Volkmar Frinken, Horst Bunke
SEMWEB
2004
Springer
15 years 3 months ago
Learning Meta-descriptions of the FOAF Network
We argue that in a distributed context, such as the Semantic Web, ontology engineers and data creators often cannot control (or even imagine) the possible uses their data or ontolo...
Gunnar Aastrand Grimnes, Peter Edwards, Alun D. Pr...
ECAL
2007
Springer
15 years 1 months ago
From the Outside-In: Embodied Attention in Toddlers
Abstract. An important goal in cognitive development research is an understanding of the real-world physical and social environment in which learning takes place. However, the rele...
Linda B. Smith, Chen Yu, Alfredo F. Pereira
GECCO
2006
Springer
159views Optimization» more  GECCO 2006»
15 years 1 months ago
Identification of weak motifs in multiple biological sequences using genetic algorithm
Recognition of motifs in multiple unaligned sequences provides an insight into protein structure and function. The task of discovering these motifs is very challenging because mos...
Topon Kumar Paul, Hitoshi Iba
ATAL
2003
Springer
15 years 1 months ago
Using web helper agent profiles in query generation
Personalized information agents can help overcome some of the limitations of communal Web information sources such as portals and search engines. Two important components of these...
Gabriel Somlo, Adele E. Howe