Timezone: »
Poster
Deep Learning with Kernel Regularization for Visual Recognition
Kai Yu · Wei Xu · Yihong Gong
In this paper we focus on training deep neural networks for visual recognition tasks. One challenge is the lack of an informative regularization on the network parameters, to imply a meaningful control on the computed function. We propose a training strategy that takes advantage of kernel methods, where an existing kernel function represents useful prior knowledge about the learning task of interest. We derive an efficient algorithm using stochastic gradient descent, and demonstrate very positive results in a wide range of visual recognition tasks.
Author Information
Kai Yu (Baidu)
Wei Xu (NEC Labs America)
Yihong Gong
Related Events (a corresponding poster, oral, or spotlight)
-
2008 Spotlight: Deep Learning with Kernel Regularization for Visual Recognition »
Tue. Dec 9th 04:38 -- 04:39 AM Room
More from the Same Authors
-
2014 Poster: Communication Efficient Distributed Machine Learning with the Parameter Server »
Mu Li · David G Andersen · Alexander Smola · Kai Yu -
2013 Demonstration: Demos of Deep Learning Technologies at Baidu IDL »
Yi Yang · Kai Yu -
2012 Poster: Deep Learning of invariant features via tracked video sequences »
Will Y Zou · Andrew Y Ng · Shenghuo Zhu · Kai Yu -
2010 Poster: Deep Coding Network »
Yuanqing Lin · Tong Zhang · Shenghuo Zhu · Kai Yu -
2009 Poster: Nonlinear Learning using Local Coordinate Coding »
Kai Yu · Tong Zhang · Yihong Gong -
2008 Poster: Stochastic Relational Models for Large-scale Dyadic Data using MCMC »
Shenghuo Zhu · Kai Yu · Yihong Gong -
2008 Spotlight: Stochastic Relational Models for Large-scale Dyadic Data using MCMC »
Shenghuo Zhu · Kai Yu · Yihong Gong -
2007 Poster: Gaussian Process Models for Link Analysis and Transfer Learning »
Kai Yu · Wei Chu -
2007 Poster: Predictive Matrix-Variate t Models »
Shenghuo Zhu · Kai Yu · Yihong Gong -
2007 Demonstration: Gender and Age Recognition »
Wei Xu · Kai Yu · Yihong Gong -
2006 Poster: Gaussian Process Models for Discriminative Link Prediction »
Kai Yu · Wei Chu · Shipeng Yu · Volker Tresp · Zhao Xu