6881 search results - page 194 / 1377 » Motivation |
131
click to vote
ESANN
2003
15 years 7 months ago
2003
In this tutorial paper about mathematical aspects of neural networks, we will focus on two directions: on the one hand, we will motivate standard mathematical questions and well st...
171
click to vote
NAACL
2004
15 years 7 months ago
2004
Maximum entropy models are a common modeling technique, but prone to overfitting. We show that using an exponential distribution as a prior leads to bounded absolute discounting b...
138
click to vote
NAACL
2004
15 years 7 months ago
2004
Many probabilistic models for natural language are now written in terms of hierarchical tree structure. Tree-based modeling still lacks many of the standard tools taken for grante...
149
click to vote
NIPS
2004
15 years 7 months ago
2004
In this paper we propose an efficient algorithm for reducing a large mixture of Gaussians into a smaller mixture while still preserving the component structure of the original mod...
179
click to vote
PARMA
2004
15 years 7 months ago
2004
In the recent years, our ability of collecting information rapidly increases and huge databases that change over time in a high frequency have been developed. On the other hand, th...