A key feature of wireless communications is the spatial reuse. However, the spatial aspect is not yet well understood for the purpose of designing efficient spectrum sharing mecha...
In this paper we consider uncountable classes recognizable by ω-automata and investigate suitable learning paradigms for them. In particular, the counterparts of explanatory, vac...
Sanjay Jain, Qinglong Luo, Pavel Semukhin, Frank S...
In the standard model of inductive inference, a learner gets as input the graph of a function, and has to discover (in the limit) a program for the function. In this paper, we cons...
A number of learning machines used in information science are not regular, but rather singular, because they are non-identifiable and their Fisher information matrices are singula...
We prove strong noise-tolerance properties of a potential-based boosting algorithm, similar to MadaBoost (Domingo and Watanabe, 2000) and SmoothBoost (Servedio, 2003). Our analysi...