Deep Learning with Kernel Regularization for Visual Recognition

In this paper we aim to train deep neural networks for rapid visual recognition. The task is highly challenging, largely due to the lack of a meaningful regularizer on the functions realized by the networks. We propose a novel regularization method that takes advantage of kernel methods, where an oracle kernel function represents prior knowledge about the recognition task of interest. We derive an efficient algorithm using stochastic gradient descent, and demonstrate encouraging results on a wide range of recognition tasks, in terms of both accuracy and speed.

• Type: Conference
• Year: 2008
• Where: NIPS
• Authors: Kai Yu, Wei Xu, Yihong Gong
• Keywords: Deep Neural Networks, Information Technology, NIPS 2008, Rapid Visual Recognition, Recognition Tasks