Question 1

Supervised learning uses a set of inputs for which the desired outputs are known.For example,a dataset of loan applications with the success or failure of borrowers to repay their loans has a set of input parameters and known outputs.

Accepted Answer

Supervised learning is a type of machine learning that involves a set of labeled input-output training examples to learn a function that can predict the output for new input data. The training data for supervised learning consists of input-output pairs, where the desired output is known or labeled. This is in contrast to unsupervised learning, where the input data is not labeled, and the algorithm tries to find patterns or structures in the data without any guidance on what the output should be.

Question 2

Weights are crucial in network information processing because they store learned patterns of information; and it is through repeated adjustments of these weights that a network learns.

Accepted Answer

Weights in a neural network are important because they store learned patterns of information, and the network learns through repeated adjustments of these weights, also known as training.

Question 3

Neural network models are designed as exact replicas of how the human brain actually functions.

Accepted Answer

While neural networks are inspired by how the human brain works, they are not exact replicas. They use simplified mathematical models of neurons and synapses to simulate learning and decision-making processes.

Question 4

Implementation of an ANN often requires interfaces with other computer-based information systems and user training.

Accepted Answer

Implementation of an ANN may require interfaces with other computer-based information systems for data input and output, as well as user training to ensure proper use and understanding of the system.

Question 5

Parallel processing resembles the way the brain and conventional computing works.

Accepted Answer

Parallel processing is a characteristic of the brain's functioning, allowing it to process multiple tasks simultaneously. Conventional computing, traditionally, relies on sequential processing, executing one instruction at a time, although modern computers can simulate parallel processing through multiple cores or processors.

Question 6

Typically,the input-output transformation process at the individual neuron level is performed in a linear fashion.

Accepted Answer

The input-output transformation process at the individual neuron level is typically performed in a nonlinear fashion. This is because the neuron's activation function is nonlinear, meaning that small changes in input can produce large changes in output, depending on where the input falls on the function's curve.

Question 7

Several types of data,such as text,pictures,and voice,can be used as inputs in network information processing.

Accepted Answer

Text, pictures, and voice can all be used as inputs in network information processing.

Question 8

In neural network,larger data sets increase processing time during training but improve the accuracy of the training and often lead to faster convergence to a good set of weights.

Accepted Answer

This statement is true. While larger data sets may increase processing time during training, they can improve the accuracy of the training and lead to faster convergence to a good set of weights. This is because larger data sets provide more information that can be used to train the network, leading to better generalization and performance on new data.

Question 9

Training of artificial neural networks is an iterative process and the iteration continues until the error sum is converged to below a preset accep level.

Accepted Answer

The statement is true. Training of artificial neural networks involves adjusting the weights and biases of the network based on the error between the predicted output and the actual output. The training process is iterated until the error reaches an acceptable level.

Question 10

In network information processing,each input corresponds to one or two attributes.

Accepted Answer

In network information processing, each input can correspond to multiple attributes, not limited to one or two, depending on the complexity of the network and the data being processed.

Question 11

In general,ANN are sui for problems whose inputs are both categorical and numeric,and where the relationships between inputs and outputs are linear or the input data are normally distributed.

Accepted Answer

ANN are suitable for problems where relationships between inputs and outputs are non-linear or complex, and where the input data may not necessarily be normally distributed. ANNs are also capable of handling only numerical inputs, not categorical inputs.

Question 12

Minotaur was implemented to prevent fraud.In the first 3 months following installation of Minotaur,the average fraud loss per case was reduced by 40 percent.

Accepted Answer

The statement clearly states that Minotaur was implemented to prevent fraud and the average fraud loss per case was reduced by 40% in the first 3 months following its installation. Therefore, the statement is true.

Question 13

A general Hopfield network is a single large layer of neurons with total interconnectivity.

Accepted Answer

A Hopfield network is indeed a single layer of neurons where each neuron is connected to every other neuron, resulting in a fully interconnected network.

Question 14

The output of a network contains the solution to a problem.

Accepted Answer

Neural networks are often used for solving complex problems, such as image recognition, natural language processing, and financial forecasting, by processing large amounts of data and producing an output. This output is often the solution to the problem being tackled by the network.

Question 15

Each ANN is composed of a collection of neurons that are grouped into three types of layers: input,intermediate (or hidden),and output.

Accepted Answer

This statement is true. An artificial neural network (ANN) consists of neurons that are organized into three types of layers: input, intermediate or hidden, and output. The input layer receives the input signals, the hidden layer processes the information, and the output layer produces the final output of the network.

Question 16

A threshold value is a hurdle value for the output of a neuron to trigger the next level of neurons.If an output value is larger than the threshold value,it will not be passed to the next level of neurons.

Accepted Answer

If an output value is larger than the threshold value, it will be passed to the next level of neurons. The threshold acts as a minimum value that the output must exceed to activate the next layer of neurons.

Question 17

Neural networks have been used in finance,marketing,manufacturing,operations,and information systems and in many business applications for pattern recognition,forecasting,prediction,and classification.

Accepted Answer

Neural networks have indeed been used in various business applications for pattern recognition, forecasting, prediction, and classification.

Question 18

The human brain is composed of special cells called neurons.Neural networks are composed of interconnected processing elements called artificial neurons.

Accepted Answer

Neural networks are designed to simulate the behavior of neurons in the human brain and are composed of interconnected processing elements called artificial neurons.

Question 19

The processing elements (PE)of an ANN are artificial neurons,which receive inputs,process them,and deliver outputs.

Accepted Answer

The statement is correct. The processing elements of an ANN are indeed artificial neurons that receive inputs, process them, and deliver outputs.

Question 20

The information processing in neural networks makes it attractive for solving complex problems.

Accepted Answer

Neural networks are modeled after the human brain and are capable of processing large amounts of information in parallel, thus making them highly efficient for solving complex problems.

Quiz 6: Artificial Neural Networks for Data Mining