Sciweavers

33 search results - page 5 / 7
» Output Regularized Metric Learning with Side Information
Sort
View
AAAI
2007
13 years 8 months ago
Kernel Regression with Order Preferences
We propose a novel kernel regression algorithm which takes into account order preferences on unlabeled data. Such preferences have the form that point x1 has a larger target value...
Xiaojin Zhu, Andrew B. Goldberg
JMLR
2012
11 years 8 months ago
Deep Learning Made Easier by Linear Transformations in Perceptrons
We transform the outputs of each hidden neuron in a multi-layer perceptron network to have zero output and zero slope on average, and use separate shortcut connections to model th...
Tapani Raiko, Harri Valpola, Yann LeCun
ECCV
2010
Springer
13 years 11 months ago
Human Attributes from 3D Pose Tracking
We show that, from the output of a simple 3D human pose tracker one can infer physical attributes (e.g., gender and weight) and aspects of mental state (e.g., happiness or sadness)...
MVA
2000
172views Computer Vision» more  MVA 2000»
13 years 7 months ago
Partial Face Extraction and Recognition Using Radial Basis Function Networks
work, applies a nonlinear transformation from the input space to the hidden space. The output layer Partial face images, e.g.1 eyes, nose, and ear supplies the response of the netw...
Nan He, Kiminori Sato, Yukitoshi Takahashi
ICML
2009
IEEE
14 years 7 months ago
BoltzRank: learning to maximize expected ranking gain
Ranking a set of retrieved documents according to their relevance to a query is a popular problem in information retrieval. Methods that learn ranking functions are difficult to o...
Maksims Volkovs, Richard S. Zemel