Hash kernels and structured learning
Vast amounts of data being generated, how to process massive data remains a challenge for machine learning algorithms. We propose hash kernels to facilitate efficient kernels which can deal with massive multi-class problems. We show a principled way to compute the kernel matrix for data streams and sparse feature spaces. We further generalise it via sampling to graphs. Later we exploit the connection between hash kernels with compressed sensing, and apply hashing to face recognition which...[Show more]
|Collections||Open Access Theses|
|Access Rights:||Open Access|
|b25699714_Shi_Qinfeng.pdf||32.3 MB||Adobe PDF|
Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.