Practical Recurrent Learning (PRL) has been proposed as a simple learning algorithm for recurrent neural networks[1][2]. This algorithm enables learning with practical order O(n2 )...
This paper proposes efficient and robust methods for tracking a moving object at multiple spatial and temporal resolution levels. The efficiency comes from optimising the amounts ...
Sumantra Dutta Roy, Son Dinh Tran, Larry S. Davis,...
Energy efficient operations are essential to increase the lifetime of wireless sensor network. A clustering-based protocol is one approach that reduces energy by a data aggregation...
The drive from the South African Government towards the adoption of open source software across all platforms, incurred a number of research and development questions. The open so...
In this paper we describe an approach that both creates crosslingual acoustic monophone model sets for speech recognition tasks and objectively predicts their performance without ...