# tut7_sol - EE4210 Solution to Tutorial 7 Learning in a 1-D...

This preview shows pages 1–2. Sign up to view the full content.

1 EE4210 Solution to Tutorial 7 Learning in a 1-D Self-Organizing Map (a) Initial input x = [ x 1 x 2 x 3 x 4 ] = [0.85 0 0.05 0.1], η = 0.6 Δ w ji ( n ) = [ x i ( n ) - w ji ( n )] for the winning neuron and neurons inside the neigbourhood Δ w ji ( n ) = 0 for all other neurons 1 st iteration ( n =0, neighbourhood size = 1) v 1 (0)= w 11 (0) x 1 + w 12 (0) x 2 + w 13 (0) x 3 + w 14 (0) x 4 = 0.10 v 2 (0)= w 21 (0) x 1 + w 22 (0) x 2 + w 23 (0) x 3 + w 24 (0) x 4 = 0.12 v 3 (0)= w 31 (0) x 1 + w 32 (0) x 2 + w 33 (0) x 3 + w 34 (0) x 4 = 0.70 (the largest output) v 4 (0)= w 41 (0) x 1 + w 42 (0) x 2 + w 43 (0) x 3 + w 44 (0) x 4 = 0.29 Neuron 3 is the winning neuron and it can have its weights updated. Δ w 31 (0) = η [ x 1 (0) - w 31 (0)] = 0.6 [0.85 – 0.82 ] = 0.018 Δ w 32 (0) = [ x 2 (0) - w 32 (0)] = 0.6 [ 0 – 0.1 ] = –0.06 Δ w 33 (0) = [ x 3 (0) - w 33 (0)] = 0.6 [ 0.05 – 0.03 ] = 0.012 Δ w 34 (0) = [ x 4 (0) - w 34 (0)] = 0.6 [ 0.1 – 0.05 ] = 0.03 Δ w 3 (0) = [0.018 –0.06 0.012 0.03] As the neighbourhood size is 1, neurons 2 and 4 can also have their weights updated. Δ

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
This is the end of the preview. Sign up to access the rest of the document.

## This note was uploaded on 04/14/2011 for the course EE 4210 taught by Professor Wong during the Spring '10 term at City University of Hong Kong.

### Page1 / 3

tut7_sol - EE4210 Solution to Tutorial 7 Learning in a 1-D...

This preview shows document pages 1 - 2. Sign up to view the full document.

View Full Document
Ask a homework question - tutors are online