BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:IC Colloquium: Programming Languages for Machine Learning and Perc
 eption
DTSTART:20190121T141500
DTEND:20190121T153000
DTSTAMP:20260407T064435Z
UID:2f4855e63dd3e5168ae57d00df6bc9d56c6ce427124576172258b674
CATEGORIES:Conferences - Seminars
DESCRIPTION:By:  Andrew Fitzgibbon - Microsoft (Cambridge)\nVideo of his t
 alk\n\nAbstract:\nIn 1957\, many (most?) computer programs were the expres
 sion of mathematical formulae in machine instructions. It was tedious\, so
  Backus and colleagues wrote the “FORmula TRANslator”\, perhaps the fi
 rst modern compiler. FORTRAN revolutionised the writing of numerical code 
 and the richness of tasks the computer could perform. Today\, we see anoth
 er resurgence in numerical programming\, in the domain of machine learning
 \, computer vision\, speech processing and other areas of “AI”. Such c
 ode needs to run fast on large datasets for “training”\, or to run ver
 y efficiently on small machines for “inference”. To serve this need\, 
 a variety of frankly clunky domain-specific tools such as TensorFlow and P
 yTorch have emerged. Like FORTRAN-1\, they are incredibly useful tools\, b
 ut there is room for improvement. I will talk about several potential impr
 ovements\, in languages from Julia to C++ to F# to Haskell\, covering with
  some rather surprising benchmarks of algorithmic differentiation tools\, 
 to compilation of functional programs to non-garbage-collected runtimes\, 
 to a new view of DSLs inspired by Julia’s slogan “it’s just code”.
  By way of introduction I will develop some of the key ideas in nonlinear 
 optimization as it applies to AI and computer vision\, at a level which I 
 plan to be accessible to all.\n\nBio:\nFitzgibbon is a partner scientist a
 t Microsoft in Cambridge\, UK. He has published numerous highly-cited pape
 rs\, and received many awards for his work\, including ten “best paper
 ” prizes at various venues\, the Silver medal of the Royal Academy of En
 gineering\, and the BCS Roger Needham award. He is a fellow of the Royal A
 cademy of Engineering\, the British Computer Society\, and the Internation
 al Association for Pattern Recognition. He studied at University College\,
  Cork\, and then did a Masters at Heriot-Watt University\, before taking u
 p an RSE job at the University of Edinburgh\, which eventually morphed int
 o a PhD. He moved to Oxford in 1996 and drove large software projects such
  as the VXL project\, and then spent several years as a Royal Society Univ
 ersity Research Fellow before joining Microsoft in 2005. He loves programm
 ing\, particularly in C++\, and his recent work has included new numerical
  algorithms for Eigen\, and compilation of F# to a non-garbage-collected r
 untime.\n\nMore information\n 
LOCATION:BC 420 https://plan.epfl.ch/?room==BC%20420
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR