tut3 - (b) The initial weights are w 1 (0) = w 2 (0) = 0...

Info iconThis preview shows page 1. Sign up to view the full content.

View Full Document Right Arrow Icon
EE4210 Tutorial 3 Train a Perceptron to perform the logical NOR function Besides using a logic gate, the logical NOR function with bipolar inputs and output defined by Table 1 can also be implemented by training a perceptron with threshold (as shown in Fig. 1). The neuronal function is < - = = 0 1 0 1 ) ( v v v y ϕ and the learning-rate parameter η = 1. x 1 x 2 Target Output d 1 1 -1 1 -1 -1 -1 1 -1 -1 -1 1 Table 1 Fig. 1 (a) The initial weights are w 1 (0) = w 2 (0) = 0 and θ (0) = 0. Use the conventional perceptron training algorithm to update the weights and find the appropriate decision boundary.
Background image of page 1
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: (b) The initial weights are w 1 (0) = w 2 (0) = 0 and (0) = 0. Use the delta rule training algorithm to update the weights and find the appropriate decision boundary. (c) Repeat (a), but this time use another set of initial weights w 1 (0) = 1, w 2 (0) = -2, and (0) = -1. (d) Repeat (b), but this time use another set of initial weights w 1 (0) = 1, w 2 (0) = -2, and (0) = -1. y x x 1 2 w 1 w 2-1...
View Full 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.

Ask a homework question - tutors are online