2934 search results - page 197 / 587 » Hypothesis Spaces for Learning |
142
click to vote
MLG
2007
Springer
16 years 19 days ago
2007
Springer
We give a universal kernel that renders all the regular languages linearly separable. We are not able to compute this kernel efficiently and conjecture that it is intractable, but...
179
click to vote
TCS
2008
15 years 6 months ago
2008
This paper studies a novel paradigm for learning formal languages from positive and negative examples which consists of mapping strings to an appropriate highdimensional feature s...
133
click to vote
SIAMCOMP
1998
15 years 6 months ago
1998
We first present an algorithm that uses membership and equivalence queries to exactly identify a discretized geometric concept defined by the union of m axis-parallel boxes in d-...
213
click to vote
IJCNN
2007
IEEE
16 years 24 days ago
2007
IEEE
Abstract— The optimal model parameters of a kernel machine are typically given by the solution of a convex optimisation problem with a single global optimum. Obtaining the best p...
130
click to vote
DAGM
2004
Springer
15 years 12 months ago
2004
Springer
We compare two approaches to the problem of estimating the depth of a point in space from observing its image position in two