11539 search results - page 356 / 2308 » On Learning from Exercises |
149
click to vote
ESANN
2003
15 years 8 months ago
2003
In this paper fully connected RTRL neural networks are studied. In order to learn dynamical behaviours of linear-processes or to predict time series, an autonomous learning algori...
196
click to vote
NIPS
1997
15 years 8 months ago
1997
Multiple-instance learning is a variation on supervised learning, where the task is to learn a concept given positive and negative bags of instances. Each bag may contain many ins...
194
click to vote
ICML
2010
IEEE
15 years 7 months ago
2010
IEEE
This paper studies the problem of learning from ambiguous supervision, focusing on the task of learning semantic correspondences. A learning problem is said to be ambiguously supe...
164
Voted
JMLR
2010
15 years 1 months ago
2010
In this paper, we study the problem of learning a matrix W from a set of linear measurements. Our formulation consists in solving an optimization problem which involves regulariza...
188
click to vote
SIGADA
2001
Springer
15 years 11 months ago
2001
Springer
Automatic software testing is gradually becoming accepted practice in the software industry. The shrinking development cycle and higher expectation of software quality are forcing...