— We consider the problem of inferring sensor positions and a topological (i.e. qualitative) map of an environment given a set of cameras with non-overlapping fields of view. In...
The problem of designing input signals for optimal generalization in supervised learning is called active learning. In many active learning methods devised so far, the bias of the...
Cognitive networking deals with applying cognition to the entire network protocol stack for achieving stack-wide as well as network-wide performance goals, unlike cognitive radios ...
Giorgio Quer, Hemanth Meenakshisundaram, Tamma Bhe...
— Backpropagation through time is a very popular discrete-time recurrent neural network training algorithm. However, the computational time associated with the learning process t...
Seeking to extend the functional capability of the elderly, we explore the use of probabilistic methods to learn and recognise human activity in order to provide monitoring suppor...