: Recurrent neural networks possess interesting universal approximation capabilities, making them good candidates for time series modeling. Unfortunately, long term dependencies ar...
Signal nding pattern discovery in unaligned DNA sequences is a fundamental problem in both computer science and molecular biology with important applications in locating regulator...
This paper is a proposal for a new two-tier calculus, designed to model aspects of CORBA-like systems at the CORBA evel. The higher object level known as Oompa abstracts away from...
Malcolm Tyrrell, Andrew Butterfield, Alexis Donnel...
With the aim to improve the quality of gazetteers for geographic information retrieval systems, we present a method to detect place names employed by people submitting information...
Florian A. Twaroch, Philip D. Smart, Christopher B...
In this paper, we explore the use of a Gaussian posteriorgram based representation for unsupervised discovery of speech patterns. Compared with our previous work, the new approach...