Can a artificial neural network capture association if input patterns is greater then dimensionality of input vectors?

By using only linear processing units in output layer, can a artificial neural network capture association if input patterns is greater then dimensionality of input vectors?

A

yes

B

no

You are the administrator of a Windows 2000 Server computer. The server contains one network adapter and is a file and print server for critical company resources. You install a second network adpater in the server and connect it to the same network subnet as the first adapter. You want to ensure that the first adapter is used for all network traffic and the second adapter is used only if the first adapter fails or is disconnected from the network. You also want to ensure that the server always has network connectivity even if one network adapter fails. What should you do?

A

Set the second adapters status to disable

B

Configure the first adapter to use a TCP/IP metric of 100

C

Configure the second adapter to use a TCP/IP metric of 25

D

Configure the binding order on the second adapter to bind TCP/IP last

E

None of above

Which of the following is true for neural networks? (i) The training time depends on the size of the network. (ii) Neural networks can be simulated on a conventional computer. (iii) Artificial neurons are identical in operation to biological ones.

A

All of the mentioned

B

(ii) is true

C

(i) and (ii) are true

D

None of the mentioned

Which of the following is true for neural networks?
(i) The training time depends on the size of the network.
(ii) Neural networks can be simulated on a conventional computer.
(iii) Artificial neurons are identical in operation to biological ones.

A

All of the mentioned

B

(ii) is true

C

(i) and (ii) are true

D

None of the mentioned

A too-large weight initialized on the neural network can lead to vanishing gradient whereas a too-small weight initialized on the neural network can lead to exploding gradient.

A

True

B

False

Your network uses TCP/IP as the only network protocol. Devices on the network are configured to use IP address from the private 10.0.0.0 range. All the client computers on the network runs Windows 2000 Professional. The network includes Windows 2000 Server computers and UNIX servers. User's print jobs are sent to shared printers on a Windows 2000 Server computer named PrintServ that directs the print jobs to print devices attached directly to the network. You have a high-capacity print device that is attached to one of the UNIX servers. The UNIX computer uses the LPR printing protocol, and it's IP address is 10.1.1.99. The name of the printer queue is GIANT. You want users to be able to connect to this printer from their computers. What should you do?

A

Install Microsoft Print Services for Unix on PrintServ. Create a network printer on users' computers, and specify that the printer URL is LPR://10.1.1.99/ GIANT

B

Install Microsoft Print Services for Unix on users* Computers. Create a network printer, and specify that the printer name is \10.1.1.99GIANT

C

Create a network printer on PrintServ, and specify that the printer name is \16.1.1.99GIANT. Share this printer and connect to it from users computers

D

Create a local printer on PrintServ. Create a new TCP/IP port for an LPR server at address 10.1.1.99 with a queue name of GIANT. Share this printer and connect to it from users' computers

E

None of above

Assume that you are given a data set and a neural network model trained on the data set. You are asked to build a decision tree model with the sole purpose of understanding/interpreting the built neural network model. In such a scenario, which among the following measures would you concentrate most on optimising?

A

accuracy of the decision tree model on the given data set

B

f1 measure of the decision tree model on the given data set

C

fidelity of the decision tree model, which is the fraction of instances on which the neural network and the decision tree give the same output

D

comprehensibility of the decision tree model, measured in terms of the size of the corresponding rule set

Given above is a description of a neural network. When does a neural network model become a deep learning model?

A

when you add more hidden layers and increase depth of neural network

B

when there is higher dimensionality of data

C

when the problem is an image recognition problem

D

when there is lower dimensionality of data

Which of the following is true? (i) On average, neural networks have higher computational rates than conventional computers. (ii) Neural networks learn by example. (iii) Neural networks mimic the way the human brain works.

A

All of the mentioned are true

B

(ii) and (iii) are true

C

(i), (ii) and (iii) are true

D

None of the mentioned

Which of the following is true?
(i) On average, neural networks have higher computational rates than conventional computers.
(ii) Neural networks learn by example.
(iii) Neural networks mimic the way the human brain works.

A

All of the mentioned are true

B

(ii) and (iii) are true

C

(i), (ii) and (iii) are true

D

None of the mentioned

Can a artificial neural network capture association if input patterns is greater then dimensionality of input vectors?

Related Questions