– Borja Balle Pigem (McGill University) : A General Framework for Learning Weighted Automata Carte non disponible Date/heure Date(s) - 4 septembre 2014 Catégories Pas de Catégories ABSTRACT : Weighted automata provide a concise algebraic parametrization for functions from strings to real numbers. This class contains many well-known\nexamples like deterministic finite automata (DFA) where values are\nbinary and hidden Markov models (HMM) where values represent\nprobabilities of strings. In this talk I will present a general framework\nbased on weighted automata which can be used to tackle a wide variety of\nlearning problems involving sequential data, including classification,\ndensity estimation, and sequence tagging. I will then show how recent\nspectral algorithms for learning stochastic languages and sequence tagging\nmodels can be derived naturally within this framework.[
– Borja Balle Pigem (McGill University) : A General Framework for Learning Weighted Automata Carte non disponible Date/heure Date(s) - 4 septembre 2014 Catégories Pas de Catégories ABSTRACT : Weighted automata provide a concise algebraic parametrization for functions from strings to real numbers. This class contains many well-known\nexamples like deterministic finite automata (DFA) where values are\nbinary and hidden Markov models (HMM) where values represent\nprobabilities of strings. In this talk I will present a general framework\nbased on weighted automata which can be used to tackle a wide variety of\nlearning problems involving sequential data, including classification,\ndensity estimation, and sequence tagging. I will then show how recent\nspectral algorithms for learning stochastic languages and sequence tagging\nmodels can be derived naturally within this framework.[