University of Cambridge > Talks.cam > Machine Learning @ CUED > Accelerating computation of SVM and DNN by binary approximation

Accelerating computation of SVM and DNN by binary approximation

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact zoubin-office.

Object detection involves classification of a huge number of detection windows obtained by raster scanning of an input image. In this talk, we introduce binary approximation to accelerate the computation of linear SVM for multi-class classification task. Since the proposed method can replace real-valued inner-product with binary inner-product computations, it’s about 200 times faster than the conventional SVM classifiers. We also show that the proposed approach can be extended to enable fast computation of existing deep neural network models and decrease model size without the need for retraining.

This talk is part of the Machine Learning @ CUED series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2017 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity