Sciweavers

3716 search results - page 143 / 744
» On the monotonization of the training set
Sort
View
FLAIRS
2007
15 years 8 months ago
Knowledge Transfer in Deep Convolutional Neural Nets
Knowledge transfer is widely held to be a primary mechanism that enables humans to quickly learn new complex concepts when given only small training sets. In this paper, we apply ...
Steven Gutstein, Olac Fuentes, Eric Freudenthal
NECO
2002
106views more  NECO 2002»
15 years 6 months ago
Learning Nonregular Languages: A Comparison of Simple Recurrent Networks and LSTM
In response to Rodriguez' recent article (2001) we compare the performance of simple recurrent nets and "Long Short-Term Memory" (LSTM) recurrent nets on context-fr...
Jürgen Schmidhuber, Felix A. Gers, Douglas Ec...
PROMISE
2010
15 years 1 months ago
On the value of learning from defect dense components for software defect prediction
BACKGROUND: Defect predictors learned from static code measures can isolate code modules with a higher than usual probability of defects. AIMS: To improve those learners by focusi...
Hongyu Zhang, Adam Nelson, Tim Menzies
KDD
2004
ACM
190views Data Mining» more  KDD 2004»
16 years 6 months ago
Kernel k-means: spectral clustering and normalized cuts
Kernel k-means and spectral clustering have both been used to identify clusters that are non-linearly separable in input space. Despite significant research, these methods have re...
Inderjit S. Dhillon, Yuqiang Guan, Brian Kulis
SAGT
2009
Springer
113views Game Theory» more  SAGT 2009»
16 years 28 days ago
Games with Congestion-Averse Utilities
Congestion games—in which players strategically choose from a set of “resources” and derive utilities that depend on the congestion on each resource— are important in a wid...
Andrew Byde, Maria Polukarov, Nicholas R. Jennings