A Generic Dataflow Programming Environment for Neural Networks

N. N. Schraudolph. A Generic Dataflow Programming Environment for Neural Networks. Technical Report IDSIA-15-00, Istituto Dalle Molle di Studi sull'Intelligenza Artificiale, 2000.

Download

91.7kB	38.9kB	25.4kB

Abstract

We describe a new programming environment for neural networks (in the widest sense) based on the notion of folded dataflow graphs. Currently under development, the system will permit visual, interactive design of all aspects of neural networks (network architecture, learning algorithm, loss function, teacher/environment, etc.) within a single, generic framework, using primitives at the level of Matlab operations. The system is being implemented in C++, and is now complete except for the graphical user interface. It has been found to provide an excellent, flexible yet efficient platform for the rapid prototyping of neural networks.

BibTeX Entry

@techreport{dean,
     author = {Nicol N. Schraudolph},
      title = {\href{http://nic.schraudolph.org/pubs/dean.pdf}{A Generic
               Dataflow Programming Environment for Neural Networks}},
     number = {IDSIA-15-00},
institution = {Istituto Dalle Molle di Studi sull'Intelligenza Artificiale},
    address = {Galleria 2, CH-6928 Manno, Switzerland},
       year =  2000,
   b2h_type = {Other},
  b2h_topic = {Other},
   abstract = {
    We describe a new programming environment for neural networks (in
    the widest sense) based on the notion of {\em folded dataflow}\/
    graphs.  Currently under development, the system will permit visual,
    interactive design of all aspects of neural networks (network
    architecture, learning algorithm, loss function, teacher/environment,
    etc.) within a single, generic framework, using primitives at the
    level of Matlab operations.
    The system is being implemented in C++, and is now complete except
    for the graphical user interface.  It has been found to provide an
    excellent, flexible yet efficient platform for the rapid prototyping
    of neural networks.
}}