CPSC-481 Quiz 4

Different learning method does not include: a. Introduction b. Analogy c. Memorization d. Deduction

a. Introduction

Neural networks are complex ___ with many parameters. a. Linear functions b. Discrete functions c. Nonlinear functions d. Binary functions

c. Nonlinear Functions

A single perceptron can computer the XOR function. (T/F)

False

For effective training of neural network, the network should have at least 5 - 10 times as many weights as there are training samples. (T/F)

False

Genetic Learning is a symbolic learning approach because it utilizes parse tree structures which are symbolic models.

False

A perceptron is guaranteed to perfectly learn a given linearly separable function within a finite number of training steps. (T/F)

True

In an unsupervised learning: a. No specific inputs are given b. Neither inputs nor outputs are given c. Both inputs and outputs are given d. Specific output values are not given e. Specific output values are given

d. Specific output values are not given