User Thomas Wagenaar

6 votes

1 answer

535 views

Recurrent networks mimicking previous / current input

asked Jul 29, 2017 at 9:24

5 votes

1 answer

2k views

Is it better to split sequences into overlapping or non-overlapping training samples?

asked Oct 7, 2020 at 7:53

5 votes

1 answer

6k views

Neural network failing because of Infinity

asked May 4, 2017 at 18:05

3 votes

2 answers

1k views

Dropout effectiveness on small neural networks

asked May 18, 2017 at 11:26

3 votes

2 answers

489 views

Is the NEAT algorithm unbalanced?

asked Mar 28, 2017 at 14:16

3 votes

2 answers

1k views

Why is the default learning rate for Adadelta so low in Keras?

asked Oct 27, 2020 at 10:48

3 votes

2 answers

2k views

Proper shape of LSTM dataset for keras

asked Feb 1, 2021 at 20:42

3 votes

2 answers

866 views

Can a convolutional NN be made with perceptrons?

asked Mar 8, 2017 at 9:20

3 votes

0 answers

350 views

Should I use random fixed mutation or random percentual mutation?

asked May 2, 2017 at 17:09

2 votes

1 answer

666 views

Normalization - which is better?

asked Apr 7, 2017 at 14:42

2 votes

1 answer

285 views

Do different species create offspring (NEAT)?

asked Apr 10, 2017 at 12:10

1 vote

1 answer

98 views

Is nested mutation effective?

asked Apr 17, 2017 at 18:33

1 vote

1 answer

421 views

Are momentum and (mini-) batch training compatible? [closed]

asked Jun 16, 2017 at 12:33

1 vote

1 answer

32 views

Testing set 40x as big as training set?

asked Jun 23, 2017 at 12:43

1 vote

0 answers

447 views

When to stop episode during reinforcement learning

asked Feb 2, 2021 at 12:47

1 vote

0 answers

52 views

Can we derive the reward function from the behaviour of a trained agent?

asked Feb 22, 2021 at 12:31

1 vote

1 answer

17 views

Should identical inputs always have shared weights to the next layer?

asked Aug 11, 2021 at 17:36

1 vote

0 answers

117 views

Forcing the mean of predictions to converge to true value

asked Dec 18, 2020 at 8:12

1 vote

0 answers

106 views

Algorithm for neuron activation order

asked Mar 21, 2017 at 11:26

Stack Exchange Network

19 Questions

Recurrent networks mimicking previous / current input

Is it better to split sequences into overlapping or non-overlapping training samples?

Neural network failing because of Infinity

Dropout effectiveness on small neural networks

Is the NEAT algorithm unbalanced?

Why is the default learning rate for Adadelta so low in Keras?

Proper shape of LSTM dataset for keras

Can a convolutional NN be made with perceptrons?

Should I use random fixed mutation or random percentual mutation?

Normalization - which is better?

Do different species create offspring (NEAT)?

Is nested mutation effective?

Are momentum and (mini-) batch training compatible? [closed]

Testing set 40x as big as training set?

When to stop episode during reinforcement learning

Can we derive the reward function from the behaviour of a trained agent?

Should identical inputs always have shared weights to the next layer?

Forcing the mean of predictions to converge to true value

Algorithm for neuron activation order