1. Reducing multiclass to binary: a unifying approach for margin classifiers;Allwein;J.Mach.Learn.Res.,2000
2. Label embedding trees for large multi-class tasks;Bengio,2010
3. An analysis of single-layer networks in unsupervised feature learning;Coates,2011
4. A gentle Hessian for efficient gradient descent;Collobert,2004
5. Torch7: a matlab-like environment for machine learning;Collobert,2011