Question: Suppose a convolutional neural network for detecting flowers is trained on images that tend to have blue flowers in the upper left corner and pink

Suppose a convolutional neural network for detecting flowers is trained on images that tend
to have blue flowers in the upper left corner and pink flowers in the lower right corner. It is
then tested on two different sets of test instances, testset 1 with blue flowers in the upper
left corner, and pink flowers in the lower right corner, testset 2 with pink flowers in the upper
left corner and blue flowers in the lower right corner. If the final layer of the network is fully
connected then:
The error rate of the network will be about the same on both test sets
The error rate of the network will be lower on testset 2 than on testset 1
The expected value of the error rate will be worse than empirical test error rate
The error rate of the network will be higher on the testset 2 than on testset 1
Suppose a convolutional neural network for

Step by Step Solution

There are 3 Steps involved in it

1 Expert Approved Answer
Step: 1 Unlock blur-text-image
Question Has Been Solved by an Expert!

Get step-by-step solutions from verified subject matter experts

Step: 2 Unlock
Step: 3 Unlock

Students Have Also Explored These Related Programming Questions!