24680 search results - page 134 / 4936 » Learning to |
172
click to vote
IJCNN
2006
IEEE
16 years 29 days ago
2006
IEEE
Abstract— Supervised learning rules for spiking neural networks are currently only able to use time-to-first-spike coding and are plagued by very irregular learning curves due t...
165
click to vote
WSC
1997
15 years 8 months ago
1997
Active and cooperative learning methods represent a paradigm shift in the delivery of engineering education. These techniques recognize that the passive model of the typical colle...
158
click to vote
PRL
2008
15 years 6 months ago
2008
We consider an active learning game within a transductive learning model. A major problem with many active learning algorithms is that an unreliable current hypothesis can mislead...
199
click to vote
ILP
2007
Springer
16 years 1 months ago
2007
Springer
In reinforcement learning problems, an agent has the task of learning a good or optimal strategy from interaction with his environment. At the start of the learning task, the agent...
177
click to vote
ICML
2000
IEEE
16 years 7 months ago
2000
IEEE
Landmarking is a novel approach to describing tasks in meta-learning. Previous approaches to meta-learning mostly considered only statistics-inspired measures of the data as a sou...