Question 1

This type of supervised network architecture does not contain a hidden layer.

Accepted Answer

A)  backpropagation 
B)  perceptron 
C)  self-organizing map 
D)  genetic 
A)  backpropagation 
B)  perceptron 
C)  self-organizing map 
D)  genetic B

Question 2

The test set accuracy of a backpropagation neural network can often be improved by

Accepted Answer

A)  increasing the number of epochs used to train the network. 
B)  decreasing the number of hidden layer nodes. 
C)  increasing the learning rate. 
D)  decreasing the number of hidden layers. 
A)  increasing the number of epochs used to train the network. 
B)  decreasing the number of hidden layer nodes. 
C)  increasing the learning rate. 
D)  decreasing the number of hidden layers. A

Question 3

Two classes each of which is represented by the same pair of numeric attributes are linearly separable if

Accepted Answer

A)  at least one of the pairs of attributes shows a curvilinear relationship between the classes. 
B)  at least one of the pairs of attributes shows a high positive correlation between the classes. 
C)  at least one of the pairs of attributes shows a high positive correlation between the classes 
D)  a straight line partitions the instances of the two classes 
A)  at least one of the pairs of attributes shows a curvilinear relationship between the classes. 
B)  at least one of the pairs of attributes shows a high positive correlation between the classes. 
C)  at least one of the pairs of attributes shows a high positive correlation between the classes 
D)  a straight line partitions the instances of the two classes D

Question 4

The total delta measures the total absolute change in network connection weights for each pass of the training data through a neural network. This value is most often used to determine the convergence of a

Accepted Answer

A)  perceptron network. 
B)  feed-forward network. 
C)  backpropagation network. 
D)  self-organizing network. 
A)  perceptron network. 
B)  feed-forward network. 
C)  backpropagation network. 
D)  self-organizing network.

This type of supervised network architecture does not contain a hidden layer.

The test set accuracy of a backpropagation neural network can often be improved by

Two classes each of which is represented by the same pair of numeric attributes are linearly separable if

The total delta measures the total absolute change in network connection weights for each pass of the training data through a neural network. This value is most often used to determine the convergence of a

Data Mining: a First View

Data Mining: a Closer Look

Basic Data Mining Techniques

An Excel-Based Data Mining Tool

Knowledge Discovery in Databases

The Data Warehouse

Formal Evaluation Techniques

Neural Networks

Statistical Techniques

Specialized Techniques

Rule-Based Systems

Managing Uncertainty in Rule-Based Systems

Intelligent Agents

Filters

Exam 9: Building Neural Networks With Ida

This type of supervised network architecture does not contain a hidden layer.

The test set accuracy of a backpropagation neural network can often be improved by

Two classes each of which is represented by the same pair of numeric attributes are linearly separable if

The total delta measures the total absolute change in network connection weights for each pass of the training data through a neural network. This value is most often used to determine the convergence of a

Data Mining: a First View

Data Mining: a Closer Look

Basic Data Mining Techniques

An Excel-Based Data Mining Tool

Knowledge Discovery in Databases

The Data Warehouse

Formal Evaluation Techniques

Neural Networks

Statistical Techniques

Specialized Techniques

Rule-Based Systems

Managing Uncertainty in Rule-Based Systems

Intelligent Agents

Filters