Sciweavers

147 search results - page 24 / 30
» On the weight dynamics of recurrent learning
Sort
View
ICML
2006
IEEE
14 years 9 months ago
Bayesian regression with input noise for high dimensional data
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...
Jo-Anne Ting, Aaron D'Souza, Stefan Schaal
ML
2002
ACM
141views Machine Learning» more  ML 2002»
13 years 8 months ago
On the Existence of Linear Weak Learners and Applications to Boosting
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...
Shie Mannor, Ron Meir
ICCV
2009
IEEE
15 years 1 months ago
Learning Deformable Action Templates from Crowded Videos
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 ...
Benjamin Yao, Song-Chun Zhu
ICML
1998
IEEE
14 years 9 months ago
Q2: Memory-Based Active Learning for Optimizing Noisy Continuous Functions
This paper introduces a new algorithm, Q2, foroptimizingthe expected output ofamultiinput noisy continuous function. Q2 is designed to need only a few experiments, it avoids stron...
Andrew W. Moore, Jeff G. Schneider, Justin A. Boya...
ICPR
2006
IEEE
14 years 9 months ago
Learning Policies for Efficiently Identifying Objects of Many Classes
Viola and Jones (VJ) cascade classification methods have proven to be very successful in detecting objects belonging to a single class -- e.g., faces. This paper addresses the mor...
Ahmed M. Elgammal, Ramana Isukapalli, Russell Grei...