no code implementations • NeurIPS 2011 • Ross B. Girshick, Pedro F. Felzenszwalb, David A. Mcallester
Compositional models provide an elegant formalism for representing the visual appearance of highly variable objects.
no code implementations • NeurIPS 2011 • Joseph Keshet, David A. Mcallester
We consider latent structural versions of probit loss and ramp loss.
no code implementations • NeurIPS 2010 • Tamir Hazan, Joseph Keshet, David A. Mcallester
In discriminative machine learning one is interested in training a system to optimize a certain desired measure of performance, or loss.