In the past ten years, boosting has become a major field of machine learning and classification. This paper brings contributions to its theory and algorithms. We first unify a ...
Theories of how the brain computes can be differentiated in three general conceptions: the algorithmic approach, the neural information processing (neurocomputational) approach an...
We give the first representation-independent hardness results for PAC learning intersections of halfspaces, a central concept class in computational learning theory. Our hardness...
We characterize the gap between time and space complexity of functions by operators and completeness. First, we introduce a new notion of operators for function complexity classes ...
In this paper we describe an improved formalisation of slicing in WSL transformation theory and apply the result to a particularly challenging slicing problem: the SCAM mug [1]. W...