Sciweavers

3556 search results - page 546 / 712
» Can machine learning be secure
Sort
View
PPSN
2010
Springer
13 years 9 months ago
Evolving a Single Scalable Controller for an Octopus Arm with a Variable Number of Segments
Abstract. While traditional approaches to machine learning are sensitive to highdimensional state and action spaces, this paper demonstrates how an indirectly encoded neurocontroll...
Brian G. Woolley, Kenneth O. Stanley
ICDM
2010
IEEE
134views Data Mining» more  ICDM 2010»
13 years 8 months ago
Consequences of Variability in Classifier Performance Estimates
The prevailing approach to evaluating classifiers in the machine learning community involves comparing the performance of several algorithms over a series of usually unrelated data...
Troy Raeder, T. Ryan Hoens, Nitesh V. Chawla
CVPR
2011
IEEE
13 years 7 months ago
Distributed Computer Vision Algorithms Through Distributed Averaging
Traditional computer vision and machine learning algorithms have been largely studied in a centralized setting, where all the processing is performed at a single central location....
Roberto Tron, René, Vidal
COLING
2010
13 years 5 months ago
Multilingual Subjectivity: Are More Languages Better?
While subjectivity related research in other languages has increased, most of the work focuses on single languages. This paper explores the integration of features originating fro...
Carmen Banea, Rada Mihalcea, Janyce Wiebe
INTERSPEECH
2010
13 years 5 months ago
Coping imbalanced prosodic unit boundary detection with linguistically-motivated prosodic features
Continuous speech input for ASR processing is usually presegmented into speech stretches by pauses. In this paper, we propose that smaller, prosodically defined units can be ident...
Yi-Fen Liu, Shu-Chuan Tseng, Jyh-Shing Roger Jang,...