Sciweavers

3 search results - page 1 / 1
» Back Propagation is Sensitive to Initial Conditions
Sort
View
71
Voted
NIPS
1990
14 years 10 months ago
Back Propagation is Sensitive to Initial Conditions
This paper explores the effect of initial weight selection on feed-forward networks learning simple functions with the back-propagation technique. We first demonstrate, through th...
John F. Kolen, Jordan B. Pollack
ICASSP
2011
IEEE
14 years 1 months ago
Superpixel-based object class segmentation using conditional random fields
Object class segmentation (OCS) is a key issue in semantic scene labeling and understanding. Its general principle consists of naming object entities into scenes according to thei...
Xi Li, Hichem Sahbi
AMAI
2004
Springer
15 years 3 months ago
Warped Landscapes and Random Acts of SAT Solving
Recent dynamic local search (DLS) algorithms such as SAPS are amongst the state-of-the-art methods for solving the propositional satisfiability problem (SAT). DLS algorithms modi...
Dave A. D. Tompkins, Holger H. Hoos