Language models for speech recognition tend to be brittle across domains, since their performance is vulnerable to changes in the genre or topic of the text on which they are trai...
Abstract. We introduce a concept of self-organizing Hybrid Neurofuzzy Networks (HNFN), a hybrid modeling architecture combining neurofuzzy (NF) and polynomial neural networks(PNN)....
Abstract—Transactional Memory (TM) is emerging as a promising technology to simplify parallel programming. While several TM systems have been proposed in the research literature,...
Chi Cao Minh, JaeWoong Chung, Christos Kozyrakis, ...
A concept of linearly graded statistical models for analogue performance evaluation is proposed and a suitable technique for automatic generation of analogue performance models us...
Architectural decisions for DSP modules are often analyzed using high level C models. Such high-level explorations allow early examination of the algorithms and the architectural ...