BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//7.2.3.1//EN
TZID:Europe/Paris
X-WR-TIMEZONE:Europe/Paris
BEGIN:VEVENT
UID:8309@i2m.univ-amu.fr
DTSTART;TZID=Europe/Paris:20140904T140000
DTEND;TZID=Europe/Paris:20140904T150000
DTSTAMP:20241120T210331Z
URL:https://www.i2m.univ-amu.fr/evenements/borja-balle-pigem-mcgill-univer
 sity-a-general-framework-for-learning-weighted-automata/
SUMMARY: (...): Borja Balle Pigem (McGill University): A General Framework 
 for Learning Weighted Automata
DESCRIPTION:: ABSTRACT: Weighted automata provide a concise algebraic param
 etrization for functions from strings to real numbers. This class contains
  many well-known\nexamples like deterministic finite automata (DFA) -- whe
 re values are\nbinary -- and hidden Markov models (HMM) -- where values re
 present\nprobabilities of strings. In this talk I will present a general f
 ramework\nbased on weighted automata which can be used to tackle a wide va
 riety of\nlearning problems involving sequential data\\\, including classi
 fication\\\,\ndensity estimation\\\, and sequence tagging. I will then sho
 w how recent\nspectral algorithms for learning stochastic languages and se
 quence tagging\nmodels can be derived naturally within this framework.
END:VEVENT
BEGIN:VTIMEZONE
TZID:Europe/Paris
X-LIC-LOCATION:Europe/Paris
BEGIN:DAYLIGHT
DTSTART:20140330T030000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
END:DAYLIGHT
END:VTIMEZONE
END:VCALENDAR