• Cortex_Pro:   Neural Network Development Tool.
  • Python module for the Brill POS Tagger  
  • Python module for the Abney parser
  • bu2 A simple backup utility

    Back to my home page


    Neural Network Development Tool

    Cortex-Pro is a neural network development tool designed by Mike Reiss and Simon Hasting
    (who started to work on it while at the Centre for Neural Networks at King's College London).

    It is a very flexible tools and the version which you can download has been expanded with:

  • New types of neuron models, nodes and connections *.
  • Additional mathematical functions *.
  • New graphics commands *.
  • Commands to read images from the WinVision B/W Frame Grabber *.
  • Image processing functions *.
  • Commands to read-in B/W PCX image files *.
  • Command to output controls to a LEGO based mobile robot.
  • I/O Functions to control a KHEPERA Robot (incl. vision turret).

  • Those marked with * can be operated in the demo version.

    Other additions are in preparation:

  • To acquire images from the QUICKCAM via the parallel port.
  • More......

  • For more information on these expansions and any question: email
    ---> Download: ) <---

    The Demonstration program runs on PCs with 4Mb+ RAM, under DOS or in a DOS window in WIN95, WIN98 and WINNT.
    To run the demo you should:
  • Make a directory of its own, e.g e:\cortex
  • Uncompress using: PKUNZIP.EXE e:\cortex\*.* (size uncompressed: 1.6Mb)
  • You get then further instructions by typing CTXHELP

  • View a screen shot cyclop.gif(78062) ), part of which was incorporated in the note:

    "A Connectionist Approach to Spatial Memory and Planning" (PDF 304K)
    Bugmann, G. (1997),
    as Chap. 5 in Landau L.J. and Taylor J.G. (eds) "Basic Concepts in Neural Networks: A survey",
    In the Series: Perspectives in Neural Networks, Springer, London, pp. 109-146. 

    Cortex-Pro was also used in following publications:

    "Note on the Use of Weight-Averaging Output Nodes in RBF-Based Mapping nets"
    Bugmann, G. (1997) (56235)
    ->(run the demo RBFWAV.CTX to see the new net!).

    "Neuro-resistive grid approach to trainable controllers: A pole balancing example".
    D'Cruz B., Bapi R. and Bugmann G. (1997)
    To appear in Neural Computing and Application Journal (ps file)(144294)
    ->(run the demo RESCART.CTX to see the pole balance!).

    "Planning and Learning Goal-Directed Sequences of Robot-Arm movements"
    Althöfer K. and Bugmann G.(1995)
    Proc. of ICANN'95, Paris, Vol. 1, 449-454. (ps file)(37402)
    ->(run the demo ARMDEM.CTX to see the robot arm move!).

    "Route finding by neural nets"
    Bugmann, G., Taylor, J.G. and Denham M. (1994)
    in Taylor J.G (ed) "Neural Networks", Alfred Waller Ltd, Henley-on-Thames, p. 217-230.
    ->(run the demo ROBODEM.CTX to see a robot solve a maze problem!).

    "Value Maps for planning and learning implemented with cellular automata "
    Bugmann G. (1996)
    in Parmee I.C. (ed) "Proc. of the 2nd International Conf. on Adaptive Computing in Engineering Design and Control (ACEDC'96)", Plymouth, 26-28 March 1996, ISBN 0 905227 61 1, p. 307-309. (30631)

    "Biologically Plausible Neural Computation"
    Bugmann G. (1997)
    Biosystems,40, pp. 11-19. (ps file)(41057)
    ->(run the demo ELIFDEM.CTX to see a motion detecting spiking neuron with partial reset!).
    ->(run the demo LIFDEM.CTX to see a spiking neuron with random inputs!).

    "Role of Temporal Integration and Fluctuation Detection in the highly irregular firing of a Leaky Integrator Neuron Model with Partial Reset".
    Bugmann G., Christodoulou C. and Taylor J.G. (1996)
    To appear in Neural Computation 


    Simple Backup Utility

    Just click on a shortcut on your desktop and all files modified since the last backup will be saved onto a CD (use the same CD for successive backups until full), in a readable format.




    Guido Bugmann, November 2005 email