3
votes
Accepted
Is it bad to average several MAEs calculated from chunks of a big test dataset?
Can I save the MAE from each chunk of data and then average them ?
Yes.
This is perfectly fine.
Why?
Think about the metric's definition.
Caveat: We assume $k$ chunks of equal chunk size $cs$.
If ...
2
votes
How to Findout if a neural network is invariant
What kind of neural network are you using?
It could be invariant if the initial weights are always the same, but some NN can also have stochastic inner mechanisms (ex, noise and minibatches).
In all ...
Only top scored, non community-wiki answers of a minimum length are eligible
Related Tags
convolutional-neural-network × 736deep-learning × 283
neural-network × 255
keras × 164
machine-learning × 155
cnn × 125
tensorflow × 118
python × 77
image-classification × 73
computer-vision × 72
convolution × 59
pytorch × 39
classification × 33
training × 25
backpropagation × 20
lstm × 17
rnn × 16
autoencoder × 16
image-recognition × 16
overfitting × 15
loss-function × 14
transfer-learning × 14
nlp × 12
dataset × 12
data-augmentation × 12