Sciweavers

4181 search results - page 437 / 837
» Evaluating Usefulness for Dynamic Classification
Sort
View
ML
1998
ACM
136views Machine Learning» more  ML 1998»
15 years 6 months ago
Co-Evolution in the Successful Learning of Backgammon Strategy
Following Tesauro’s work on TD-Gammon, we used a 4000 parameter feed-forward neural network to develop a competitive backgammon evaluation function. Play proceeds by a roll of t...
Jordan B. Pollack, Alan D. Blair
JCDL
2003
ACM
99views Education» more  JCDL 2003»
15 years 12 months ago
Structural Analysis of Musical Signals for Indexing and Thumbnailing
A musical piece typically has a repetitive structure. Analysis of this structure will be useful for music segmentation, indexing and thumbnailing. This paper presents an algorithm...
Wei Chai, Barry Vercoe
EUROPAR
2006
Springer
15 years 10 months ago
Comparison of Different Methods for Next Location Prediction
Next location prediction anticipates a person's movement based on the history of previous sojourns. It is useful for proactive actions taken to assist the person in an ubiquit...
Jan Petzold, Faruk Bagci, Wolfgang Trumler, Theo U...
CEC
2008
IEEE
16 years 1 months ago
Auto-tuning fuzzy granulation for evolutionary optimization
—Much of the computational complexity in employing evolutionary algorithms as optimization tool is due to the fitness function evaluation that may either not exist or be computat...
Mohsen Davarynejad, Mohammad R. Akbarzadeh-Totonch...
ICPADS
1994
IEEE
15 years 10 months ago
Efficient Fault Tolerance: An Approach to Deal with Transient Faults in Multiprocessor Architectures
Dynamic error processing approaches are an important mechanism to increase the reliability in a multiprocessor system, while making efficient use of the available resources. To th...
Andrea Bondavalli, Silvano Chiaradonna, Felicita D...