CS 7643 Quiz 3 NEWEST VERSION 2025 Exam
Guide Questions and Verified Answers |
100% Correct.
Modeling Error
Given a particular NN architecture, the actual model that represents the real
world may not be in that space.
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
Invariance
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
saliency maps
, Where G is the Gram matrix that abstracts the correlation between the layers
Content Loss
the difference in content features between the synthesized image and the
content image via the squared loss function
Binary Cross-Entropy Loss
-1* log(prediction of true class)
Balanced Cross-Entropy Loss
-1 alpha log(prediction of true class)
Focal Loss
-1 (1- prediction of true class)^gamma log(prediction of true class)
Class Balanced Focal Loss
-1 alpha_t (1- prediction of true class)^gamma log(prediction of true class)
SSD (Single-Shot Detector)
grid as anchors w different scales/aspect ratios
Based on VGG model till conv5_3 layer
YOLO (You Only Look Once)
single-scale
faster for same size
Customized architecture, full connected at the end
NMS before results
R-CNN
Guide Questions and Verified Answers |
100% Correct.
Modeling Error
Given a particular NN architecture, the actual model that represents the real
world may not be in that space.
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
Invariance
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
saliency maps
, Where G is the Gram matrix that abstracts the correlation between the layers
Content Loss
the difference in content features between the synthesized image and the
content image via the squared loss function
Binary Cross-Entropy Loss
-1* log(prediction of true class)
Balanced Cross-Entropy Loss
-1 alpha log(prediction of true class)
Focal Loss
-1 (1- prediction of true class)^gamma log(prediction of true class)
Class Balanced Focal Loss
-1 alpha_t (1- prediction of true class)^gamma log(prediction of true class)
SSD (Single-Shot Detector)
grid as anchors w different scales/aspect ratios
Based on VGG model till conv5_3 layer
YOLO (You Only Look Once)
single-scale
faster for same size
Customized architecture, full connected at the end
NMS before results
R-CNN
