Connectionists: Postdocs / Research Programmer for Compositional Learning via Generalized Automatic Differentiation

[Barak A. Pearlmutter]

                     Postdocs / Research Programmer
                                  for
   Compositional Learning via Generalized Automatic Differentiation

The goal of this project is to make a qualitative improvement in our
ability to write sophisticated numeric code, by giving numeric
programmers access to _fast_, _robust_, _general_, _accurate_
differentiation operators.

To be technical: we are adding exact first-class derivative
calculation operators (Automatic Differentiation or AD) to the lambda
calculus, and embodying the combination in a production-quality fast
system suitable for numeric computing in general, and compositional
machine learning methods in particular.  Our research prototype
compilers generate object code competitive with the fastest current
systems, which are based on FORTRAN.  And the combined expressive
power of first-class AD operators and function programming allows very
succinct code for many machine learning algorithms, as well as for
some algorithms in computer vision and signal processing.  Specific
sub-projects include: compiler and numeric programming environment
construction; writing, simplifying, and generalising, machine learning
and other numeric algorithms; and associated Type Theory/Lambda
Calculus/PLT/Real Computation issues.

TO THE PROGRAMMING LANGUAGE COMMUNITY, we seek to contribute a way to
make numeric software faster, more robust, and easier to write.

TO THE MACHINE LEARNING COMMUNITY, in addition to making it easier to
write efficient numeric codes, we seek to contribute a system that
embodies "compositionality", in that gradient optimisation can be
automatically and efficiently performed on systems themselves
consisting of many components, even when such components may
internally take derivatives or perform optimisation.  (Examples of
this include, say, optimisation of the rules of a multi-player game to
cause the players' actions to satisfy some desiderata, where the
players themselves optimise their own strategies using simple models
of their opponents which they optimise according to their opponents'
observed behaviour.)

To this end, we are seeking to fill three positions (postdoctoral or
research programmer, or in exceptional cases graduate students) with
interest and experience in at least one of: programming language
theory, automatic differentiation, machine learning, numerics,
mathematical logic.

Informal announcement: http://www.bcl.hamilton.ie/~barak/ad-fp-positions.html

Formal job postings on http://humanresources.nuim.ie/vacancies.shtml, in
particular
http://humanresources.nuim.ie/documents/JobSpecPostdoc2_Final.pdf and
http://humanresources.nuim.ie/documents/JobSpecProgrammer_Final.pdf


Inquiries to:
--
Barak A. Pearlmutter <barak at cs.nuim.ie>
Hamilton Institute & Dept Computer Science
NUI Maynooth, Co. Kildare, Ireland