This paper presents novel analysis results for input-to-state stability (ISS) that utilise dynamic programming techniques to characterise minimal ISS gains and transient bounds. Th...
Shoudong Huang, Matthew R. James, Dragan Nesic, Pe...
We consider the existence of a linear weak learner for boosting algorithms. A weak learner for binary classification problems is required to achieve a weighted empirical error on t...
Boosting is a simple yet powerful modeling technique that is used in many machine learning and data mining related applications. In this paper, we propose a novel scale-space based...
Standard hybrid learners that use domain knowledge require stronger knowledge that is hard and expensive to acquire. However, weaker domain knowledge can benefit from prior knowle...
We consider equational theories for functions defined via recursion involving equations between closed terms with natural rules based on recursive definitions of the function symb...