A Hopfield Neural Network Applet

Controls for the applet

Use the mouse to enter a pattern by clicking squares inside the rectangle "on" or "off". Then, have the network store your pattern by pressing "i", for impose. After storing some patterns, try entering a new pattern, and then press the space bar repeatedly to watch the network "settle" into a previously imposed state. The following keyboard commands are recognized:

• c : clear display
• n : clear memory
• i : impose current pattern into memory (self-connects = 0)
• I : impose current pattern into memory (self-connects set by GHR)
• r : generate a random new pattern (pattern is not imposed on weights, though)
• h : set state to upper half of display off, lower half on (pattern is not imposed, though)
• q : force repaint
• s : Toggle settling on and off
• space : Settle one step
• d : debug -- print state on stdout

Thanks to Matt Hill, at IBM's TJ Watson Research Center, Hawthorne, NY, author of this applet, and to James Bontempo for adding double-buffering to reduce flicker.