—This paper considers the problem of temporally fusing classifier outputs to improve the overall diagnostic classification accuracy in safety-critical systems. Here, we discuss d...
The paper describes the IBM systems submitted to the NIST Rich Transcription 2007 (RT07) evaluation campaign for the speechto-text (STT) and speaker-attributed speech-to-text (SAST...
Credit assignment is a fundamental issue for the Learning Classifier Systems literature. We engage in a detailed investigation of credit assignment in one recent system called UC...
In the present work we describe architectural concepts of the distributed molecular simulation package GridMD. The main purpose of this work is to underline the construction patter...
High dimensional data that lies on or near a low dimensional manifold can be described by a collection of local linear models. Such a description, however, does not provide a glob...
Sam T. Roweis, Lawrence K. Saul, Geoffrey E. Hinto...