CS 7643 QUIZ 1 UPDATED ACTUAL EXAM QUESTIONS CORRECT ANSWERS GRADED A PLUS
Question:
Equivariance.
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 change to input causes equal
change to output
Question:
Invariance.
Answer:
If the input changes, the output stays the same. That is f(g(x)) = f(x) E.g. rotating/scaling a number
will still result in that number being classified the same. change to input does not affect output
Useful if we care more about if a feature is present than exactly where it is
Question:
saliency maps.
Answer:
Instead of using deconvnets, can, instead of taking the error gradient wrt model parameters, take
gradient of class score we're trying to visualize wrt to the image itself (the input of the network) gets
the degree to which a pixel contributed to that class score take absolute value of score because we
care about degree, not direction helps us understand why model gives response they did Another
method to make saliency maps: guided backpropagation algorithm (combination of deconvnet and
gradient of class score wrt input of network) Sensitivity of loss to individual pixel changes, uses
pre-softmax scores (gradient, then absval, then sum across channels)
, Question:
CAM = Class Activation Mapping.
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
Question:
Grad-CAM.
Answer:
more versatile version of CAM that can produce visual explanations for any arbitrary CNN, even if
the network contains a stack of fully connected layers too let the gradients of any target concept
score flow into the final convolutional layer; then compute an importance score based on the
gradients and produce a coarse localization map highlighting the important regions in the image for
predicting that concept What regions of image is model looking at to make prediction? Which
individual regions have highest class activation as you extract layer from CNN?
Direction/magnitude of gradients to determine which gradients are causing the most updates to the
NN Objective: inspective given layer of CNN and correlate to output Task specific (if asked what is
a dog -> dog pixels are more important)
Question:
Adversarial examples.
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.
Question:
Guided Backprop.
Answer:
Question:
Equivariance.
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 change to input causes equal
change to output
Question:
Invariance.
Answer:
If the input changes, the output stays the same. That is f(g(x)) = f(x) E.g. rotating/scaling a number
will still result in that number being classified the same. change to input does not affect output
Useful if we care more about if a feature is present than exactly where it is
Question:
saliency maps.
Answer:
Instead of using deconvnets, can, instead of taking the error gradient wrt model parameters, take
gradient of class score we're trying to visualize wrt to the image itself (the input of the network) gets
the degree to which a pixel contributed to that class score take absolute value of score because we
care about degree, not direction helps us understand why model gives response they did Another
method to make saliency maps: guided backpropagation algorithm (combination of deconvnet and
gradient of class score wrt input of network) Sensitivity of loss to individual pixel changes, uses
pre-softmax scores (gradient, then absval, then sum across channels)
, Question:
CAM = Class Activation Mapping.
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
Question:
Grad-CAM.
Answer:
more versatile version of CAM that can produce visual explanations for any arbitrary CNN, even if
the network contains a stack of fully connected layers too let the gradients of any target concept
score flow into the final convolutional layer; then compute an importance score based on the
gradients and produce a coarse localization map highlighting the important regions in the image for
predicting that concept What regions of image is model looking at to make prediction? Which
individual regions have highest class activation as you extract layer from CNN?
Direction/magnitude of gradients to determine which gradients are causing the most updates to the
NN Objective: inspective given layer of CNN and correlate to output Task specific (if asked what is
a dog -> dog pixels are more important)
Question:
Adversarial examples.
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.
Question:
Guided Backprop.
Answer:
