Background: The aim of protein design is to predict amino-acid sequences compatible with a given target structure. Traditionally envisioned as a purely thermodynamic question, thi...
: The k nearest neighbor classification (k-NN) is a very simple and popular method for classification. However, it suffers from a major drawback, it assumes constant local class po...
The current Internet only supports best-effort traffic. New high-speed technologies such as ATM (asynchronous transfer mode), gigabit Ethernet, fast Ethernet, and frame relay, have...
Bobby Vandalore, Wu-chi Feng, Raj Jain, Sonia Fahm...
In this paper we present a method for learning classspecific
features for recognition. Recently a greedy layerwise
procedure was proposed to initialize weights of deep
belief ne...
Mohammad Norouzi (Simon Fraser University), Mani R...
We propose a linear programming relaxation scheme for the class of multiple object tracking problems where the inter-object interaction metric is convex and the intraobject term q...