Sciweavers

3068 search results - page 319 / 614
» Separation Results on the
Sort
View
MCS
2005
Springer
16 years 6 days ago
Exploiting Class Hierarchies for Knowledge Transfer in Hyperspectral Data
Abstract. Obtaining ground truth for hyperspectral data is an expensive task. In addition, a number of factors cause the spectral signatures of the same class to vary with location...
Suju Rajan, Joydeep Ghosh
COLT
2001
Springer
15 years 11 months ago
Robust Learning - Rich and Poor
A class C of recursive functions is called robustly learnable in the sense I (where I is any success criterion of learning) if not only C itself but even all transformed classes Î...
John Case, Sanjay Jain, Frank Stephan, Rolf Wiehag...
CSR
2008
Springer
15 years 8 months ago
From Invariants to Canonization in Parallel
A function f of a graph is called a complete graph invariant if two given graphs G and H are isomorphic exactly when f(G) = f(H). If additionally, f(G) is a graph isomorphic to G, ...
Johannes Köbler, Oleg Verbitsky
DM
2010
140views more  DM 2010»
15 years 6 months ago
Online Ramsey games for triangles in random graphs
In the online F-avoidance edge-coloring game with r colors, a graph on n vertices is generated by at each stage randomly adding a new edge. The player must color each new edge as ...
József Balogh, Jane Butterfield
TNN
2008
96views more  TNN 2008»
15 years 6 months ago
Global Convergence and Limit Cycle Behavior of Weights of Perceptron
In this paper, it is found that the weights of a perceptron are bounded for all initial weights if there exists a nonempty set of initial weights that the weights of the perceptron...
Charlotte Yuk-Fan Ho, Bingo Wing-Kuen Ling, Hak-Ke...