CS 7643 Quiz 3 Study Guide
1. Modeling Error: Given a particular NN architecture, the actual model that repre-
sents the real world may not be in that space.
When model complexity increases, modeling error reduces, but optimization error
increases.
2. Estimation Error: Even if finding the best hypothesis, weights, and parameters
that minimize training error, may not generalize to test set
3. Optimization Error: Even if your NN can perfectly model the world, your algo may
not find good weights that model the function.
When model complexity increases, modeling error reduces, but optimization error
increases.
4. Effectiveness of transfer learning under certain conditions: 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.
1/
12
, 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)
5. AlexNet: 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
2/
12
1. Modeling Error: Given a particular NN architecture, the actual model that repre-
sents the real world may not be in that space.
When model complexity increases, modeling error reduces, but optimization error
increases.
2. Estimation Error: Even if finding the best hypothesis, weights, and parameters
that minimize training error, may not generalize to test set
3. Optimization Error: Even if your NN can perfectly model the world, your algo may
not find good weights that model the function.
When model complexity increases, modeling error reduces, but optimization error
increases.
4. Effectiveness of transfer learning under certain conditions: 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.
1/
12
, 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)
5. AlexNet: 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
2/
12
