CS 7643 CS7643 Quiz 2 Latest

CS 7643 / CS7643 Quiz 2 (Latest Update 2025 / 2026) Deep Learning | Questions & Answers | Grade A | 100% Correct - Georgia Tech

Question:

Transfer learning

Answer:

Reuse the features on a new dataset, that were learned previously on a large- scale dataset.

• Train features on a large-scale dataset
• Replace the last FC layer with one of our categories, and initialize with

random weights.

• Continue train on the new dataset

a.) Finetune - update all parameters b.) Freeze - update parameters only of the new FC layer - suggested if not enough new data is available

• / 3

Question:

Transfer learning effectiveness

Answer:

Works well if:

>> Source data is large, but target data is pretty small >> Generalizes across tasks (object recognition params can be used for object detection) Limitations >> Target data/task is completely different (silhoutte, contour) >> Target data is large --> the random initialization is better

Question:

Power law region

Answer:

If data set SIZE increases in LOG scale than generalization ERROR decreases LINEARLY in LOG scale

• / 3

Question:

Gradient based image optimization

Answer:

• ) Start with random/zero image
• ) Add to the input image (I) the gradient w.r.t the score of a class (Sc) x

learning rate

• ) Regularization (???)

Question:

Adversarial images

Answer:

Images, on which gradient-based optimization was performed, but on incorrect class. This small change fools the network, but the picture still looks like the original class for humans. (example image about panda)

Question:

Can a change of a single pixel change the entire class prediction?

Answer:

Yes

• / 3