Question 1)a) Using a multilayer feed-forward neural network, show the calculations for learning by the backpropagation algorithm. Let the learning rate be 0.9. Initial weight and bias values of the network are given in table below. The first training sample, X=(1,0,1), whose class lable is 1.
W14 W15 W24 W25 W34 W35 W46 W56 Θ Θ Θ
0.2 -0.3 0.4 0.1 -0.5 0.2 -0.3 -0.2 -0.4 0.2 0.1
Question 2)a) Write typical k-medoids algorithm for partitioning based on medoid. Also, describe 4 cases of the cost function for k-medoids clustering with help of diagram.
b) What are the various categories of Hierarchical Clustering? Describe BIRCH technique of cluster representation in large databases with example.
Question 3) Write brief notes on:
i) FP(Frequent Pattern) – Tree
ii) Prediction Models
iii) Web Mining