Sciweavers

1062 search results - page 14 / 213
» Sublinear Optimization for Machine Learning
Sort
View
FOCI
2007
IEEE
14 years 2 months ago
Almost All Learning Machines are Singular
— A learning machine is called singular if its Fisher information matrix is singular. Almost all learning machines used in information processing are singular, for example, layer...
Sumio Watanabe
CCS
2009
ACM
14 years 2 months ago
A framework for quantitative security analysis of machine learning
We propose a framework for quantitative security analysis of machine learning methods. Key issus of this framework are a formal specification of the deployed learning model and a...
Pavel Laskov, Marius Kloft
NECO
2010
136views more  NECO 2010»
13 years 6 months ago
Learning to Represent Spatial Transformations with Factored Higher-Order Boltzmann Machines
To allow the hidden units of a restricted Boltzmann machine to model the transformation between two successive images, Memisevic and Hinton (2007) introduced three-way multiplicat...
Roland Memisevic, Geoffrey E. Hinton
ICALT
2003
IEEE
14 years 29 days ago
Supporting Social Awareness: Requirements for Educational CVE
Social awareness is essential for effective learning. However, natural environments do not always provide optimal support for it. We analyze the potentials of Collaborative Virtua...
Ekaterina Prasolova-Førland, Monica Divitin...
AIMSA
2006
Springer
13 years 11 months ago
Machine Learning for Spoken Dialogue Management: An Experiment with Speech-Based Database Querying
Although speech and language processing techniques achieved a relative maturity during the last decade, designing a spoken dialogue system is still a tailoring task because of the ...
Olivier Pietquin