This paper presents the design of an associative memory with feedback that is capable of on-line temporal sequence learning. A framework for on-line sequence learning has been prop...
Hierarchical matrices (H-matrices) approximate matrices in a data-sparse way, and the approximate arithmetic for H-matrices is almost optimal. In this paper we present an algebrai...
Two parallel block tridiagonalization algorithms and implementations for dense real symmetric matrices are presented. Block tridiagonalization is a critical pre-processing step for...
The present paper proposes new approaches for recommendation tasks based on one-class support vector machines (1-SVMs) with graph kernels generated from a Laplacian matrix. We intr...
act 11 We address the problem of designing a network built on several layers. This problem occurs in practical applications 12 but has not been studied extensively from the point o...