CS 7643 Quiz 3 Latest Update 2025-2026 40
Questions and 100% Verified Correct Answers
Guaranteed A+
Adversarial examples - CORRECT ANSWER: Inputs formed by applying small but
intentionally worst-case perturbations to examples from the dataset, such that the
perturbed input results in the model outputting an incorrect answer with high confidence.
AlexNet - CORRECT ANSWER:
2x(CONV=>MAXPOOL=>NORM)=>3xCONV=>MAXPOOL=>3xFC
ReLU, specialized normalization layers, PCA-based data augmentation, Dropout,
Ensembling (used 7 NN with different random weights)
Critical development: More depth and ReLU
Balanced Cross-Entropy Loss - CORRECT ANSWER: -1 * alpha * log(prediction of true
class)
Binary Cross-Entropy Loss - CORRECT ANSWER: -1* log(prediction of true class)
CAM = Class Activation Mapping - CORRECT ANSWER: use Global Average Pooling
layer as final layer to average the activations of each feature map and run through
softmax loss layer to highlight the important regions of the image by projecting back the
weights of the output on the convolutional feature maps
Class Balanced Focal Loss - CORRECT ANSWER: -1 * alpha_t (1- prediction of true
class)^gamma * log(prediction of true class)
Content Loss - CORRECT ANSWER: the difference in content features between the
synthesized image and the content image via the squared loss function
, Convolutional layers and how they work (forward/backward) - CORRECT ANSWER:
https://www.youtube.com/watch?v=Lakz2MoHy6o&t=1299s
(Don't have a good short summary)
Effectiveness of transfer learning under certain conditions - CORRECT ANSWER:
Remove last FC layer of CNN and initialize it randomly, then run new data through
network to train only that layer
In order to train the NN for transfer learning -freeze the CNN layers or early layers and
learn parameters in the FC layers.
Performs very well on very small amount of training, if similar to the original data
Does not work very well if the target task's dataset is very different
If you have enough data in the target domain, and is different than the source, better to
just train on the new data
Transfer learning = reuse features we learn on a very large dataset on a completely new
thing
Steps:
Train on very large dataset
Take custom dataset and initialize network with weights trained in Step 1 (replace last
fully connected layer since classes in new network will be different)
Final step -> continue training on new dataset
Can either retrain all weights ("finetune") or freeze (ie: not update) weights in certain
layers (freezing reduces number of parameters that you need to learn)
Equivariance - CORRECT ANSWER: If the input changes, the output changes in the
same way if f(g(x) =g(f(x). If the beak of a bird in a picture moves a bit, the output values
will move in the same way
Questions and 100% Verified Correct Answers
Guaranteed A+
Adversarial examples - CORRECT ANSWER: Inputs formed by applying small but
intentionally worst-case perturbations to examples from the dataset, such that the
perturbed input results in the model outputting an incorrect answer with high confidence.
AlexNet - CORRECT ANSWER:
2x(CONV=>MAXPOOL=>NORM)=>3xCONV=>MAXPOOL=>3xFC
ReLU, specialized normalization layers, PCA-based data augmentation, Dropout,
Ensembling (used 7 NN with different random weights)
Critical development: More depth and ReLU
Balanced Cross-Entropy Loss - CORRECT ANSWER: -1 * alpha * log(prediction of true
class)
Binary Cross-Entropy Loss - CORRECT ANSWER: -1* log(prediction of true class)
CAM = Class Activation Mapping - CORRECT ANSWER: use Global Average Pooling
layer as final layer to average the activations of each feature map and run through
softmax loss layer to highlight the important regions of the image by projecting back the
weights of the output on the convolutional feature maps
Class Balanced Focal Loss - CORRECT ANSWER: -1 * alpha_t (1- prediction of true
class)^gamma * log(prediction of true class)
Content Loss - CORRECT ANSWER: the difference in content features between the
synthesized image and the content image via the squared loss function
, Convolutional layers and how they work (forward/backward) - CORRECT ANSWER:
https://www.youtube.com/watch?v=Lakz2MoHy6o&t=1299s
(Don't have a good short summary)
Effectiveness of transfer learning under certain conditions - CORRECT ANSWER:
Remove last FC layer of CNN and initialize it randomly, then run new data through
network to train only that layer
In order to train the NN for transfer learning -freeze the CNN layers or early layers and
learn parameters in the FC layers.
Performs very well on very small amount of training, if similar to the original data
Does not work very well if the target task's dataset is very different
If you have enough data in the target domain, and is different than the source, better to
just train on the new data
Transfer learning = reuse features we learn on a very large dataset on a completely new
thing
Steps:
Train on very large dataset
Take custom dataset and initialize network with weights trained in Step 1 (replace last
fully connected layer since classes in new network will be different)
Final step -> continue training on new dataset
Can either retrain all weights ("finetune") or freeze (ie: not update) weights in certain
layers (freezing reduces number of parameters that you need to learn)
Equivariance - CORRECT ANSWER: If the input changes, the output changes in the
same way if f(g(x) =g(f(x). If the beak of a bird in a picture moves a bit, the output values
will move in the same way
