2
votes
What may cause the CNN layer weight regularizer to reduce the model accuracy
In general, I stumbled across voices in literature that we shouldn't use dropout with such a big parameter for shallow networks, as it can violate their capabilities.
Example:
Piotrowski, A. P., ...
1
vote
Why Relu is correct for CNN?
Welcome to the DataScience stack exchange. ReLu is not "correct" or "incorrect" but it is just one of several popular choices for a nonlinearity in neural networks.
It sounds like ...
1
vote
Converting a Standard LSTM RNN over to a Transformer Model
With a bit of elastic net, dynamic gradient clipping and adjustments to the transformer model build training is progressing nicely now.
Here is the build that fixed it:
...
1
vote
Adding multi-image context to a CNN
You can perform individual image classification using as input the whole set of related images as well. In order to do this, your initial input will be some 3d array of stacked 256x256 matrices and ...
Only top scored, non community-wiki answers of a minimum length are eligible
Related Tags
cnn × 1365deep-learning × 508
machine-learning × 363
neural-network × 341
keras × 295
tensorflow × 207
image-classification × 171
python × 154
convolutional-neural-network × 125
convolution × 91
classification × 81
computer-vision × 77
lstm × 54
pytorch × 53
image-recognition × 44
object-detection × 43
transfer-learning × 38
rnn × 37
time-series × 35
dataset × 35
loss-function × 34
accuracy × 31
training × 29
image-preprocessing × 27
overfitting × 25