This paper addresses the problem of discriminative training of language models that does not require any transcribed acoustic data. We propose to minimize the conditional entropy ...
Program verifiers based on first-order theorem provers model the program heap as a collection of mutable maps. In such verifiers, preserving unmodified facts about the heap acr...
Because of the changing nature of spam, a spam filtering system that uses machine learning will need to be dynamic. This suggests that a case-based (memory-based) approach may work...
Sarah Jane Delany, Padraig Cunningham, Lorcan Coyl...
Relational instance-based learning (RIBL) algorithms offer high prediction capabilities. However, they do not scale up well, specially in domains where there is a time bound for c...
Abstract. Generic programming enables the programmer to define functions by induction on the structure of types. Defined once, such a generic function can be used to generate a s...