Sciweavers

173 search results - page 11 / 35
» Semi-supervised Learning on Directed Graphs
Sort
View
WIRN
2005
Springer
14 years 2 months ago
Recursive Neural Networks and Graphs: Dealing with Cycles
Recursive neural networks are a powerful tool for processing structured data. According to the recursive learning paradigm, the input information consists of directed positional ac...
Monica Bianchini, Marco Gori, Lorenzo Sarti, Franc...
ICML
2007
IEEE
14 years 9 months ago
Learning random walks to rank nodes in graphs
Ranking nodes in graphs is of much recent interest. Edges, via the graph Laplacian, are used to encourage local smoothness of node scores in SVM-like formulations with generalizat...
Alekh Agarwal, Soumen Chakrabarti
ECML
2007
Springer
14 years 13 days ago
Efficient Continuous-Time Reinforcement Learning with Adaptive State Graphs
Abstract. We present a new reinforcement learning approach for deterministic continuous control problems in environments with unknown, arbitrary reward functions. The difficulty of...
Gerhard Neumann, Michael Pfeiffer, Wolfgang Maass
EDBT
2009
ACM
277views Database» more  EDBT 2009»
14 years 1 months ago
G-hash: towards fast kernel-based similarity search in large graph databases
Structured data including sets, sequences, trees and graphs, pose significant challenges to fundamental aspects of data management such as efficient storage, indexing, and simila...
Xiaohong Wang, Aaron M. Smalter, Jun Huan, Gerald ...
ICCS
2007
Springer
14 years 2 months ago
Learning Common Outcomes of Communicative Actions Represented by Labeled Graphs
We build a generic methodology based on learning and reasoning to detect specific attitudes of human agents and patterns of their interactions. Human attitudes are determined in te...
Boris Galitsky, Boris Kovalerchuk, Sergei O. Kuzne...