| http://www.w3.org/ns/prov#value | - This provides an interesting alternative to probabilistic models such as HMM and CRF. Preliminary experiments on tay datasets and USPS character reconstruction show promising results.EPrint Type:Conference or Workshop Item (Oral)Project Keyword:Project Keyword UNSPECIFIEDSubjects:Learning/Statistics & OptimisationTheory & AlgorithmsID Code:6648Deposited By:Romain HeraultDeposited On:08 March 2010[
|
