This paper introduces a new algorithm, Q2, foroptimizingthe expected output ofamultiinput noisy continuous function. Q2 is designed to need only a few experiments, it avoids stron...
Andrew W. Moore, Jeff G. Schneider, Justin A. Boya...
Appropriately designing sampling policies is highly important for obtaining better control policies in reinforcement learning. In this paper, we first show that the least-squares ...
This paper presents two k-winners-take-all (k-WTA) networks with discontinuous activation functions. The k-WTA operation is first converted equivalently into linear and quadratic ...
Active appearance models (AAMs) are generative parametric models commonly used to track faces in video sequences. A limitation of AAMs is they are not robust to occlusion. A recen...
Protein function prediction is an active area of research in bioinformatics. And yet, transfer of annotation on the basis of sequence or structural similarity remains widely used ...