HOW TO SUBMIT HOMEWORKS

Assignment#1:LOADING AND EDITING MODULE : DUE TO NOVEMBER 13, 2007

• It should display 10 patterns pairs (U,Y) that you determine, where U is a 12x12 (12 rows, 12 columns) pattern and corresponding Y is a 8x8 pattern
• Each pattern pair (U,Y) should have a check box to mark them as being selected for training (this will be functional in assignments #2 and #3 )
• There should be buttons for training and recall (classify) operations which will be functional in assignments #2 and #3
• It should be possible to select a pattern pair for loading by a mouse click on it
• There should be a larger grid pair (12x12 and 8x8) to display the loaded pattern pairs
• It should be possible to add noise seperately either to U or to Y component of pattern pair loaded on the larger grids
• It should be possible to edit seperately either U or Y component of pattern pair loaded on the larger grids
• It should be possible to clear seperately either U or Y component of pattern pair loaded on the larger grids
• There should be a help button to explain the operation of the applet
• You may use any additional item that you feel necessary
• On your applet canvas reserve some empty area considering assignments #2 and #3 for not having difficulty later

Assignment#2:  BIDRECTIONAL ASSOCIATIVE MEMORY: DUE TO DECEMBER 4, 2007

• Implement discrete BAM network functioning as associative memory
• The patterns are to be the same as defined in assignment#1
• The patterns are to be loaded, edited and selected for training as defined in assignment#1
• Activate buttons for training and recall operations
• In addition to the larger grid pair for loading and editing the selected pattern as implemented in assignment#1, there should be another pair of large grids to display the recalled pattern pair
• During recall, display not only the final state but also the intermediate states of the network one after another on the grid reserved for recall
• You may use any additional items that you feel necessary

Assignment#3: MULTILAYER PERCEPTRON BY BACK PROPAGATION DUE TO DECEMBER 25, 2007

• Implement Multilayer Perceptron having tanh as output function trained by Backpropagation Algorithm
• The patterns are to be the same as defined in assignment#1
• The patterns are to be loaded, edited and selected for training as as defined in assignment#1
• Activate train and classify buttons
• It should be possible to set the number of neurons in the hidden layers but being assigned default values that you find appropriate
• Notice that the number of neurons at the input layer should be 144 (=12x12) which is the size of the U patterns to be trained. The number of neurons at the output layer should be the 64(=8x8) which is the size of the Y patterns.
• There should be help button to explain the operation of the applet
• You may use any additional items that you feel necessary