New answers tagged backpropagation
3
votes
Accepted
Seq2seq with RNNs, how is the training loop performed?
In seq2seq RNN training, we usually use a technique called "teacher forcing." With teacher forcing, the actual (ground truth) output word at each timestep is fed as input to the decoder in ...
0
votes
Do Artificial Neural Network with non-linear activation only in the output layer follows linearity?
If you have a sigmoid activation in your output layer, and linearities before, you can interpret it as a logistic regression model for binary classification (if ...
0
votes
Do Artificial Neural Network with non-linear activation only in the output layer follows linearity?
You are speaking about generalized linear models (GLM)
- 149
Top 50 recent answers are included
Related Tags
backpropagation × 240neural-networks × 148
deep-learning × 55
gradient-descent × 43
machine-learning × 38
convolutional-neural-networks × 36
training × 16
reinforcement-learning × 15
objective-functions × 15
math × 14
recurrent-neural-networks × 11
feedforward-neural-networks × 11
optimization × 9
weights × 9
relu × 9
activation-functions × 8
python × 6
terminology × 6
cross-entropy × 6
sigmoid × 5
calculus × 5
vanishing-gradient-problem × 5
multilayer-perceptrons × 5
comparison × 4
long-short-term-memory × 4