Sciweavers

2623 search results - page 250 / 525
» Universal Learning Theory
Sort
View
STOC
2000
ACM
174views Algorithms» more  STOC 2000»
15 years 11 months ago
Noise-tolerant learning, the parity problem, and the statistical query model
We describe a slightly subexponential time algorithm for learning parity functions in the presence of random classification noise, a problem closely related to several cryptograph...
Avrim Blum, Adam Kalai, Hal Wasserman
ATAL
2008
Springer
15 years 8 months ago
No-regret learning and a mechanism for distributed multiagent planning
We develop a novel mechanism for coordinated, distributed multiagent planning. We consider problems stated as a collection of single-agent planning problems coupled by common soft...
Jan-P. Calliess, Geoffrey J. Gordon
KER
2007
90views more  KER 2007»
15 years 6 months ago
PLTOOL: A knowledge engineering tool for planning and learning
AI planning solves the problem of generating a correct and efficient ordered set of instantiated activities, from a knowledge base of generic actions, which when executed will tra...
Susana Fernández, Daniel Borrajo, Raquel Fu...
CHI
2006
ACM
16 years 7 months ago
"Sketching" nurturing creativity: commonalities in art, design, engineering and research
icians or philosophers use abstract symbols to derive formulas or form proofs. Indeed, these sketches are structural geometric proofs, consistent with Plato's supposition that...
Kumiyo Nakakoji, Atau Tanaka, Daniel Fallman
ICPR
2004
IEEE
16 years 7 months ago
To FRAME or not to FRAME in Probabilistic Texture Modelling?
The maximum entropy principle is a cornerstone of FRAME (Filters, RAndom fields, and Maximum Entropy) model considered at times as a first-ever step towards a universal theory of ...
Georgy L. Gimel'farb, Luc J. Van Gool, Alexey Zale...