Residual gradient (RG) was proposed as an alternative to TD(0) for policy evaluation when function approximation is used, but there exists little formal analysis comparing them ex...
We consider the problem of PAC-learning distributions over strings, represented by probabilistic deterministic finite automata (PDFAs). PDFAs are a probabilistic model for the gen...
This paper points out some drawbacks and proposes some modifications to the conventional layer-by-layer BP algorithm. In particular, we present a new perspective to the learning ra...
Xu-Qin Li, Fei Han, Tat-Ming Lok, Michael R. Lyu, ...
Semantic web is an emerging paradigm that has great potential for the management of web content in a meaningful manner. With more and more semantic information appended to web, th...
A new algorithm for on-line learning linear-threshold functions is proposed which efficiently combines second-order statistics about the data with the ”logarithmic behavior” ...