New answers tagged recurrent-neural-networks
1
vote
How can I deal with random weights initialisation when predicting a time-series sine function?
From comments, you are testing your ideas with a very small neural networks.
The highly variable end result with large dependency on initial conditions is a common result of working with small numbers ...
Top 50 recent answers are included
Related Tags
recurrent-neural-networks × 354neural-networks × 118
long-short-term-memory × 100
deep-learning × 59
machine-learning × 53
natural-language-processing × 45
convolutional-neural-networks × 40
time-series × 33
tensorflow × 24
transformer × 18
comparison × 17
attention × 17
keras × 16
reference-request × 14
sequence-modeling × 14
feedforward-neural-networks × 12
gated-recurrent-unit × 12
backpropagation × 11
prediction × 11
classification × 10
training × 10
terminology × 10
python × 10
seq2seq × 10
papers × 9