97 search results - page 14 / 20 » Herding dynamical weights to learn |
131
click to vote
ICANN
2005
Springer
15 years 7 months ago
2005
Springer
Spike synchronisation and de-synchronisation are important for feature binding and separation at various levels in the visual system. We present a model of complex valued neuron ac...
112
click to vote
IJON
2006
15 years 1 months ago
2006
The goal of the visual correspondence problem is to establish a connectivity pattern (a mapping) between two images such that features projected from the same scene point are conn...
ICML
2006
IEEE
16 years 2 months ago
2006
IEEE
This paper examines high dimensional regression with noise-contaminated input and output data. Goals of such learning problems include optimal prediction with noiseless query poin...
118
Voted
ML
2002
ACM
15 years 1 months ago
2002
ACM
We consider the existence of a linear weak learner for boosting algorithms. A weak learner for binary classification problems is required to achieve a weighted empirical error on t...
128
click to vote
ICCV
2009
IEEE
16 years 6 months ago
2009
IEEE
In this paper, we present a Deformable Action Template
(DAT) model that is learnable from cluttered real-world
videos with weak supervisions. In our generative model,
an action ...