4947 search results - page 368 / 990 » Learning Module Networks |
146
click to vote
ICONIP
2008
15 years 6 months ago
2008
Abstract. While injecting fault during training has long been demonstrated as an effective method to improve fault tolerance of a neural network, not much theoretical work has been...
113
click to vote
AAAI
2004
15 years 6 months ago
2004
We describe a formal framework for diagnosis and repair problems that shares elements of the well known partially observable MDP and cost-sensitive classification models. Our cost...
125
click to vote
ESANN
1998
15 years 6 months ago
1998
We describe a new approach to real time learning of unknown functions based on an interpolating wavelet estimation. We choose a subfamily of a wavelet basis relying on nested hiera...
129
Voted
NIPS
1996
15 years 6 months ago
1996
Real-valued random hidden variables can be useful for modelling latent structure that explains correlations among observed variables. I propose a simple unit that adds zero-mean G...
124
Voted
ICIP
2001
IEEE
16 years 6 months ago
2001
IEEE
In the last years, the interest for advanced video-based surveillance applications is more and more growing. This is especially true in the field of railway urban transport where ...