Presentation

Neural Network

1. Bidirectional Associative Memory (BAM)  Submitted To: Submitted By: Dr. Meenakshi Sood Sachin Maithani Associate Professor M.E. Regular

2. TABLE OF CONTENT 1. INTRODUCTION 2.OBJECTIVE OF BAM 3.ARCHITECTURE 4. ALGORITHM 5.EXAMPLE BASED BAM 6.APPLICATION 7. LIMITATION 8.REFERENCES

3. INTRODUCTION Bidirectional Associative Memory (BAM) is a supervised learning model in Artificial Neural Network. This is  hetero-associative memory , for an input pattern, it returns another pattern which is potentially of a different size A   Recurrent Neural Network (RNN)  is needed to receive a pattern of one set of neurons as an input and generate a related, but different, output pattern of another set of neurons.

4. OBJECTIVE OF BAM A network model is to store hetero-associative pattern pairs This is used to retrieve a pattern given a noisy or incomplete pattern.

5. ARCHITECTURE When BAM accepts an input of  n -dimensional vector  X  from set  A  then the model recalls  m -dimensional vector  Y  from set  B . Similarly when  Y  is treated as input, the BAM recalls  X .

6. ALGORITHM 1. Storage (Learning):   In this learning step of BAM, weight matrix is calculated between M pairs of patterns (fundamental memories) are stored in the synaptic weights of the network following the equation

7. 2. Testing:   We have to check that the BAM recalls perfectly    for corresponding   and recalls   for corresponding Using, All pairs should be recalled accordingly. 3. Retrieval:  For an unknown vector  X  (a corrupted or incomplete version of a pattern from set  A  or  B ) to the BAM and retrieve a previously stored association

8. Initialize the BAM:                                                  Calculate the BAM output at iteration       :                                                   Update the input vector     :                                                               Repeat  the iteration until convergence, when input and output remain unchanged.

9. EXAMPLE BASED BAM Set A: Input Patterns Set B: Corresponding Target Patterns

10. Step 1:  Here, the value of M (no of pairs of patterns) is 4. Step 2:  Assign the neurons in the input and output layer. Here, neurons in the input layer are 6 and the output layer are 3 Step 3:  Now, compute the Weight Matrix (W):

11. Step 4:   Test the BAM model learning algorithm- for the input patterns BAM will return the corresponding target patterns as output. And for each of the target patterns, BAM will return the corresponding input patterns. Test on input patterns (Set A) using-

12. Test on target patterns (Set B) using - Here, for each of the input patterns, the BAM model will give correct target patterns and for target patterns, the model will also give corresponding input patterns. This signifies the bidirectional association in memory or model network.

13. APPLICATION 1. Pattern recognition 2.  Image processing

14. LIMITATION Storage capacity of the BAM:  In the BAM, stored number of associations should not be exceeded the number of neurons in the smaller layer. Incorrect convergence:  Always the closest association may not be produced by BAM.

15. REFERENCES https://www.geeksforgeeks.org/ann-bidirectional-associative-memory-bam/ https://dl.acm.org/doi/10.1145/2431211.2431217 https://www.youtube.com/watch?v=rpwrJOzWOws