9841 search results - page 1807 / 1969 » Distributed Value Functions |
181
click to vote
JMLR
2010
15 years 1 months ago
2010
We consider a supervised learning setting in which the main cost of learning is the number of training labels and one can obtain a single label for a bag of examples, indicating o...
169
click to vote
MICRO
2010
IEEE
15 years 1 months ago
2010
IEEE
We present Task Superscalar, an abstraction of instruction-level out-of-order pipeline that operates at the tasklevel. Like ILP pipelines, which uncover parallelism in a sequential...
203
click to vote
ML
2010
ACM
15 years 1 months ago
2010
ACM
Traditional classification methods assume that the training and the test data arise from the same underlying distribution. However, in several adversarial settings, the test set is...
168
click to vote
SIAMCO
2010
15 years 1 months ago
2010
This work is concerned with identification of Hammerstein systems whose outputs are measured by quantized sensors. The system consists of a memoryless nonlinearity that is polynomi...
176
click to vote
TCSV
2010
15 years 1 months ago
2010
We describe a method for achieving perceptually minimal video distortion over packet-erasure networks using perceptually unequal loss protection (PULP). There are two main ingredie...