This paper develops bounds on out-of-sample error rates for support vector machines (SVMs). The bounds are based on the numbers of support vectors in the SVMs rather than on VC di...
We propose a new lattice reduction method. Our algorithm approximates shortest lattice vectors up to a factor ≤ (k/6)n/2k and makes use of Grover’s quantum search algorithm. Th...
—Upper and lower bounds are derived for the decoding complexity of a general lattice L. The bounds are in terms of the dimension n and the coding gain
of L, and are obtained ba...
In this paper we proposed a visual speech recognition network based on Support Vector Machines. Each word of the dictionary is modeled by a set of temporal sequences of visemes. E...
In this paper we propose a modication of the Hopeld neural networks for vector precoding, based on Lenstra, Lenstra, and Lov`asz lattice basis reduction. This precoding algorithm c...