This perspective paper explores principles of unsupervised learning and how they relate to face recognition. Dependency coding and information maximization appear to be central pr...
Abstract. We study the problem of minimizing the maximum latency of flows in networks with congestion. We show that this problem is NP-hard, even when all arc latency functions ar...
We prove that there is a polynomial time substitution (y1, . . . , yn) := g(x1, . . . , xk) with k << n such that whenever the substitution instance A(g(x1, . . . , xk)) of ...
Fingerprinting is a technique for generating a representation-independent functional signature for a game playing agent. Fingerprints can be used to compare agents across represent...
We present a theory for constructing linear subspace approximations to face-recognition algorithms and empirically demonstrate that a surprisingly diverse set of face-recognition a...