Sciweavers

172 search results - page 4 / 35
» Learning predictive representations from a history
Sort
View
ATAL
2008
Springer
13 years 9 months ago
Approximate predictive state representations
Predictive state representations (PSRs) are models that represent the state of a dynamical system as a set of predictions about future events. The existing work with PSRs focuses ...
Britton Wolfe, Michael R. James, Satinder P. Singh
ICML
2009
IEEE
14 years 8 months ago
Proto-predictive representation of states with simple recurrent temporal-difference networks
We propose a new neural network architecture, called Simple Recurrent Temporal-Difference Networks (SR-TDNs), that learns to predict future observations in partially observable en...
Takaki Makino
ICMI
2009
Springer
123views Biometrics» more  ICMI 2009»
14 years 2 months ago
Learning and predicting multimodal daily life patterns from cell phones
In this paper, we investigate the multimodal nature of cell phone data in terms of discovering recurrent and rich patterns in people’s lives. We present a method that can discov...
Katayoun Farrahi, Daniel Gatica-Perez
KDD
2001
ACM
163views Data Mining» more  KDD 2001»
14 years 7 months ago
Learning to recognize brain specific proteins based on low-level features from on-line prediction servers
During the last decade, the area of bioinformatics has produced an overwhelming amount of data, with the recently published draft of the human genome being the most prominent exam...
Henrik Boström, Joakim Cöster, Lars Aske...
KDD
2009
ACM
196views Data Mining» more  KDD 2009»
14 years 2 months ago
WhereNext: a location predictor on trajectory pattern mining
The pervasiveness of mobile devices and location based services is leading to an increasing volume of mobility data. This side effect provides the opportunity for innovative meth...
Anna Monreale, Fabio Pinelli, Roberto Trasarti, Fo...