Sciweavers

129 search results - page 15 / 26
» Case Retrieval Using Nonlinear Feature-Space Transformation
Sort
View
JMLR
2012
11 years 10 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
KDD
2004
ACM
179views Data Mining» more  KDD 2004»
14 years 8 months ago
1-dimensional splines as building blocks for improving accuracy of risk outcomes models
Transformation of both the response variable and the predictors is commonly used in fitting regression models. However, these transformation methods do not always provide the maxi...
David S. Vogel, Morgan C. Wang
MVA
2008
13 years 7 months ago
Retrieving articulated 3-D models using medial surfaces
Abstract We consider the use of medial surfaces to represent symmetries of 3-D objects. This allows for a qualitative abstraction based on a directed acyclic graph of components an...
Kaleem Siddiqi, Juan Zhang, Diego Macrini, Ali Sho...
BMVC
2002
13 years 10 months ago
Practical Generation of Video Textures using the Auto-Regressive Process
Recently, there have been several attempts at creating `video textures', that is, synthesising new (potentially infinitely long) video clips based on existing ones. One way t...
Neill W. Campbell, Colin J. Dalton, David P. Gibso...
ICTAI
2007
IEEE
14 years 1 months ago
Photometric Invariant Projective Registration Using ECC Maximization
The ability of an algorithm to accurately estimate the parameters of the geometric transformation which aligns two image profiles even in the presence of photometric distortions ...
Georgios D. Evangelidis, Emmanouil Z. Psarakis