New answers tagged hidden-layers
2
I am also wondering about this.
It must depend both on convolutional sub-network output size (N) and number of classes (M).
Maybe there are some rules of thumbs depending on (N, M).
Why 2 dense layers and not, say, 3 or 4 ?
Is it better to have all dense layers (except last) the same size ? or decreasing ? or increasing ? or pyramidal ?
Is it better to have ...
Top 50 recent answers are included
Related Tags
hidden-layers × 41neural-networks × 26
deep-learning × 10
machine-learning × 6
deep-neural-networks × 5
activation-function × 5
hyperparameter-optimization × 5
recurrent-neural-networks × 4
feedforward-neural-network × 4
tensorflow × 3
ai-design × 3
long-short-term-memory × 3
regression × 3
artificial-neuron × 3
hyper-parameters × 3
convolutional-neural-networks × 2
natural-language-processing × 2
keras × 2
backpropagation × 2
models × 2
multilayer-perceptron × 2
fully-connected-layer × 2
comparison × 1
image-recognition × 1
terminology × 1