2566 search results - page 24 / 514 » Relating reinforcement learning performance to classificatio... |
109
click to vote
CVPR
2008
IEEE
16 years 1 months ago
2008
IEEE
To learn a new visual category from few examples, prior knowledge from unlabeled data as well as previous related categories may be useful. We develop a new method for transfer le...
ICDM
2002
IEEE
15 years 4 months ago
2002
IEEE
We empirically evaluate the performance of various reinforcement learning methods in applications to sequential targeted marketing. In particular, we propose and evaluate a progre...
ICML
2005
IEEE
16 years 16 days ago
2005
IEEE
This paper describes the use of machine learning to improve the performance of natural language question answering systems. We present a model for improving story comprehension th...
ICMLA
2008
15 years 1 months ago
2008
In reinforcement learning, it is a common practice to map the state(-action) space to a different one using basis functions. This transformation aims to represent the input data i...
ESANN
2008
15 years 1 months ago
2008
Standard learning procedures are better fitted to estimation than to classification problems, and focusing the training on appropriate samples provides performance advantages in cl...