NIPS
2003
13 years 6 months ago
2003
We consider the question of how well a given distribution can be approximated with probabilistic graphical models. We introduce a new parameter, effective treewidth, that captures...
NIPS
2003
13 years 6 months ago
2003
Most machine learning researchers perform quantitative experiments to estimate generalization error and compare algorithm performances. In order to draw statistically convincing c...
NIPS
2003
13 years 6 months ago
2003
The design of cooperative multi-robot systems is a highly active research area in robotics. Two lines of research in particular have generated interest: the solution of large, wea...
NIPS
2003
13 years 6 months ago
2003
The maximisation of information transmission over noisy channels is a common, albeit generally computationally difficult problem. We approach the difficulty of computing the mutua...
NIPS
2003
13 years 6 months ago
2003
NIPS
2003
13 years 6 months ago
2003
Learning from ambiguous training data is highly relevant in many applications. We present a new learning algorithm for classification problems where labels are associated with se...
NIPS
2003
13 years 6 months ago
2003
We consider the policy search approach to reinforcement learning. We show that if a “baseline distribution” is given (indicating roughly how often we expect a good policy to v...
NIPS
2003
13 years 6 months ago
2003
Many problems in information processing involve some form of dimensionality reduction. In this paper, we introduce Locality Preserving Projections (LPP). These are linear projecti...
NIPS
2003
13 years 6 months ago
2003
NIPS
2003
13 years 6 months ago
2003
A balanced network leads to contradictory constraints on memory models, as exemplified in previous work on accommodation of synfire chains. Here we show that these constraints can...