Tools

Parallel and distributed processing - II: Constraint satisfaction neural network models

  1. Click on the "click" button below "click here to see Hinton Diagrams".
  2. Click on "Click here to see the original hinton diagram with preset weights" to load the hinton diagram for the already trained network with current weights.
  3. Hover your mouse over any of the rectangles for units to see it's hinton diagram in zoomed up version towards the bottom of the canvas.
  4. Click on the "back" button to go back to the menu for more choices.
  5. Click on the "Click here to further train the model".
  6. Click on any room choice to select descriptors for that room.
  7. Click on any descriptors you wish to attribute to the room choice that you made.
  8. After making atleast one selection of descriptor for each room type, click on "train model and show Hinton Diagram".
  9. Hover your mouse over any of the rectangles for units to see it's new hinton diagram in zoomed up version towards the bottom of the canvas.
  10. Click on the "back" button to go back to the page to select room and descriptors for that room.
  11. Click on "reset" button to reset descriptors and room choices.
  12. Click on the "back" button to go back to the menu for more choices.
  13. Click on the "home" button to go back to the main menu.
  14. Click on the "click here for clamping descriptors"
  15. Click on atleast one descriptor to clamp it.
  16. Click on descriptor again to unclamp it.
  17. Click on "test network" to run 16 cycles of the network.
  18. Click on a descriptor to clamp it and simultaneously see the change in the network.
  19. Click on "reset" button to reset the clamping.
  20. lick on "Home" button to go back to the main menu.