2
votes
What what will happen if all the layers of a MLP or any DL architecture are set as same in the beginning?
There is no correlation between underfitting/overfitting with the initialization of the weights.
The problem with initialization of the weight is related to 2 main things:
Back propagation: if you ...
Only top scored, non community-wiki answers of a minimum length are eligible
Related Tags
neural-network × 4126machine-learning × 1611
deep-learning × 1367
keras × 621
python × 462
tensorflow × 404
cnn × 331
classification × 308
convolutional-neural-network × 244
lstm × 226
rnn × 224
regression × 171
backpropagation × 160
nlp × 155
image-classification × 144
training × 127
time-series × 124
loss-function × 124
gradient-descent × 120
convolution × 104
pytorch × 101
optimization × 87
activation-function × 84
autoencoder × 81
dataset × 78