Assignment #5

ECE449, Intelligent Systems in Engineering

Points: 10

Due: Thursday, October 24, 2019, 3:30 PM,

in the assignment box in the ETLC atrium

Note: Show your work! Marks are allocated

for technique and not just the answer.

1. [2 points] Consider a single-input neuron

The input to the neuron is 3.0, its weight is 2.3 and bias is -3.0.

a) What is the net input to the transfer function, tot ?

b) Using an activation function of your choice, determine output of the neuron.

2. [3 points] Consider two single-neuron perceptrons with the same weight and bias values

The first perceptron uses the unipolar hardlimit function, 𝑓hlu, and the second perceptron uses the bipolar

hardlimit function, 𝑓hlb. If the networks are given the same input x, and updated with the perceptron

learning rule, will their weights continue to have the same value?

3. [5 points] Consider two types of activation functions

Logistic sigmoid

tot +e

y= −

1

1

(covered in class), and Elliott

+tot

tot

y =

1

(new in this assignment).

a) Determine derivatives of these functions,

b) Plot graphs of the functions and their derivatives,

c) Compare the functions and describe your observations.

Student Name:

ID Number: