Learning to predict through Probabilistic Incremental Program Evolution and automatic task decomposition

Created by W.Langdon from gp-bibliography.bib Revision:1.3973

@TechReport{Salustowicz:1998:atdpipeTR,
  author =       "Rafal Salustowicz and Juergen Schmidhuber",
  title =        "Learning to predict through Probabilistic Incremental
                 Program Evolution and automatic task decomposition",
  institution =  "IDSIA",
  year =         "1998",
  type =         "Technical Report",
  number =       "IDSIA-11-98",
  address =      "Switzerland",
  keywords =     "genetic algorithms, genetic programming",
  URL =          "ftp://ftp.idsia.ch/pub/rafal/TR-11-98-filter_pipe.ps.gz",
  abstract =     "Analog gradient-based recurrent neural nets can learn
                 complex prediction tasks. Most, however, tend to fail
                 in case of long minimal time lags between relevant
                 training events. On the other hand, discrete methods
                 such as search in a space of event-memori- zing
                 programs are not necessarily affected at all by long
                 time lags: we show that discrete {"}Probabilistic
                 Incremental Program Evolution{"} (PIPE) can solve
                 several long time lag tasks that have been successfully
                 solved by only one analog method ({"}Long Short- Term
                 Memory{"} - LSTM). In fact, sometimes PIPE even
                 outperforms LSTM. Existing discrete methods, however,
                 cannot easily deal with problems whose solutions
                 exhibit comparatively high algorithmic complexity. We
                 overcome this drawback by introducing filtering, a
                 novel, general, data-driven divide-and-conquer
                 technique for automatic task decomposition that is not
                 limited to a particular learning method. We compare
                 PIPE plus filtering to various analog recurrent net
                 methods.",
  notes =        "genetic-programming@cs.stanford.edu Thu, 17 Sep 1998
                 07:01:21 -0700 (PDT)",
  size =         "pages",
}

Genetic Programming entries for Rafal Salustowicz Jurgen Schmidhuber

Citations