966 search results - page 51 / 194 » A Two-Level Learning Method for Generalized Multi-instance P... |
128
click to vote
ACL
1998
15 years 3 months ago
1998
We present a connectionist architecture and demonstrate that it can learn syntactic parsing from a corpus of parsed text. The architecture can represent syntactic constituents, an...
141
click to vote
ICML
2001
IEEE
16 years 3 months ago
2001
IEEE
Direct policy search is a practical way to solve reinforcement learning problems involving continuous state and action spaces. The goal becomes finding policy parameters that maxi...
116
click to vote
CIKM
2006
Springer
15 years 6 months ago
2006
Springer
In practical classification, there is often a mix of learnable and unlearnable classes and only a classifier above a minimum performance threshold can be deployed. This problem is...
108
Voted
ICML
2003
IEEE
16 years 3 months ago
2003
IEEE
Hierarchical reinforcement learning is a general framework which attempts to accelerate policy learning in large domains. On the other hand, policy gradient reinforcement learning...
145
click to vote
KDD
2006
ACM
16 years 2 months ago
2006
ACM
Kernel machines have been shown as the state-of-the-art learning techniques for classification. In this paper, we propose a novel general framework of learning the Unified Kernel ...