Special applications: Face recognition & Neural style transfer >> Convolutional Neural Networks

*Please Do Not Click On The Options.

* If You Click Mistakenly Then Please Refresh The Page To Get The Right Answers.

1 point

True

False

1 point

Given how few images we have per person, we need to apply transfer learning.

We need to solve a one-shot learning problem.

This allows us to learn to predict a person’s identity using a softmax output unit, where the number of classes equals the number of persons in the database plus 1 (for the final “not in database” class).

This allows us to learn to recognize a new person given just a single image of that person.

1 point

True

False

1 point

max(||f(A)-f(N)||^2 – ||f(A)-f(P)||^2 + α), 0)
max(||f(A)-f(P)||^2 – ||f(A)-f(N)||^2 + α), 0)
max(||f(A)-f(P)||^2 – ||f(A)-f(N)||^2 – α), 0)
max(||f(A)-f(N)||^2 – ||f(A)-f(P)||^2 – α), 0)

$max(||f(A)-f(N)||^2 – ||f(A)-f(P)||^2 + \alpha, 0$

The upper and lower neural networks have different input images, but have exactly the same parameters.

1 point

True

False

1 point

True

False

1 point

True

False

1 point

True

False

1 point

The regularization parameters

The pixel values of the generated image

The pixel values of the content image

The neural network parameters

1 point

30x30x30x32

30x30x30x16

Undefined: This convolution step is impossible and cannot be performed because the dimensions specified don’t match up.

Special applications: Face recognition & Neural style transfer >> Convolutional Neural Networks

Special applications: Face recognition & Neural style transfer

Related Questions & Answers:

Leave a Comment Cancel reply